Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Abstract

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features---using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.

Extended tech report

References in corpus (4)

• What makes for effective detection proposals?
• Convolutional Feature Masking for Joint Object and Stuff Segmentation
• How good are detection proposals, really?
• Object Detection Networks on Convolutional Feature Maps

Cited by in corpus (3083)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Deep Residual Learning for Image Recognition
• A Survey on Visual Transformer
• Simple Online and Realtime Tracking
• Transformers in Vision: A Survey
• Res2Net: A New Multi-scale Backbone Architecture
• Bootstrap your own latent: A new approach to self-supervised Learning
• YOLOX: Exceeding YOLO Series in 2021
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• Improved Baselines with Momentum Contrastive Learning
• HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification
• Deformable DETR: Deformable Transformers for End-to-End Object Detection
• GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
• UnitBox: An Advanced Object Detection Network
• FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Semantic Foggy Scene Understanding with Synthetic Data
• AMC: AutoML for Model Compression and Acceleration on Mobile Devices
• VisualBERT: A Simple and Performant Baseline for Vision and Language
• Person Re-identification: Past, Present and Future
• Momentum Contrast for Unsupervised Visual Representation Learning
• The VIA Annotation Software for Images, Audio and Video
• Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
• All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda
• Contrastive Representation Learning: A Framework and Review
• FCOS: Fully Convolutional One-Stage Object Detection
• Multi-Task Learning for Dense Prediction Tasks: A Survey
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Richer Convolutional Features for Edge Detection
• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• Anabranch Network for Camouflaged Object Segmentation
• A Survey of Human-in-the-loop for Machine Learning
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Learning Representations by Maximizing Mutual Information Across Views
• OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• Video Salient Object Detection via Fully Convolutional Networks
• What Makes for Good Views for Contrastive Learning?
• The ApolloScape Open Dataset for Autonomous Driving and its Application
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• This Looks Like That: Deep Learning for Interpretable Image Recognition
• Binary Neural Networks: A Survey
• YOLACT++: Better Real-time Instance Segmentation
• EfficientDet: Scalable and Efficient Object Detection
• Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Network
• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
• FPGA-based Accelerators of Deep Learning Networks for Learning and Classification: A Review
• Prototypical Contrastive Learning of Unsupervised Representations
• Deep Clustering for Unsupervised Learning of Visual Features
• 3D Object Detection for Autonomous Driving: A Survey
• YOLOP: You Only Look Once for Panoptic Driving Perception
• Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era
• Deep Continuous Fusion for Multi-Sensor 3D Object Detection
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• RetinaFace: Single-stage Dense Face Localisation in the Wild
• Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark
• Exploring Simple Siamese Representation Learning
• Facial Landmark Detection: a Literature Survey
• Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
• Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources
• Aggregated Residual Transformations for Deep Neural Networks
• Deep Learning for UAV-based Object Detection and Tracking: A Survey
• TransTrack: Multiple Object Tracking with Transformer
• SINet: A Scale-insensitive Convolutional Neural Network for Fast Vehicle Detection
• INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps
• Early Convolutions Help Transformers See Better
• Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
• SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
• Cooperative Perception for 3D Object Detection in Driving Scenarios using Infrastructure Sensors
• A Simple Semi-Supervised Learning Framework for Object Detection
• A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving
• Multimodal End-to-End Autonomous Driving
• WebVision Database: Visual Learning and Understanding from Web Data
• The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
• An Iterative BP-CNN Architecture for Channel Decoding
• LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images
• Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers
• Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
• Working Memory Connections for LSTM
• VLP: A Survey on Vision-Language Pre-training
• TransCrowd: weakly-supervised crowd counting with transformers
• Hard Negative Mixing for Contrastive Learning
• Apple Flower Detection using Deep Convolutional Networks
• A Normalized Gaussian Wasserstein Distance for Tiny Object Detection
• Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach
• Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
• Visual Question Answering: Datasets, Algorithms, and Future Challenges
• A Dataset And Benchmark Of Underwater Object Detection For Robot Picking
• BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs
• Image De-raining Using a Conditional Generative Adversarial Network
• CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images
• Monitoring COVID-19 social distancing with person detection and tracking via fine-tuned YOLO v3 and Deepsort techniques
• Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art
• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
• Deep Learning for Generic Object Detection: A Survey
• PP-YOLO: An Effective and Efficient Implementation of Object Detector
• GridMask Data Augmentation
• Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
• RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization
• LXMERT: Learning Cross-Modality Encoder Representations from Transformers
• Automatic Colon Polyp Detection using Region based Deep CNN and Post Learning Approaches
• Joint Activity Recognition and Indoor Localization with WiFi Fingerprints
• Stand-Alone Self-Attention in Vision Models
• Strengths and Weaknesses of Deep Learning Models for Face Recognition Against Image Degradations
• GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
• Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
• Revisiting Anchor Mechanisms for Temporal Action Localization
• Real-Time Apple Detection System Using Embedded Systems With Hardware Accelerators: An Edge AI Application
• DeepIM: Deep Iterative Matching for 6D Pose Estimation
• BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
• Driver Drowsiness Detection Model Using Convolutional Neural Networks Techniques for Android Application
• A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
• Weakly Supervised Fine-Grained Image Categorization
• Learning to Compose and Reason with Language Tree Structures for Visual Grounding
• Patch-VQ: 'Patching Up' the Video Quality Problem
• K-Net: Towards Unified Image Segmentation
• GhostNets on Heterogeneous Devices via Cheap Operations
• AutoAssign: Differentiable Label Assignment for Dense Object Detection
• Recurrently Exploring Class-wise Attention in A Hybrid Convolutional and Bidirectional LSTM Network for Multi-label Aerial Image Classification
• SCALE-Sim: Systolic CNN Accelerator Simulator
• Deep Hough Transform for Semantic Line Detection
• Deep Learning Techniques for Future Intelligent Cross-Media Retrieval
• Unifying Vision-and-Language Tasks via Text Generation
• An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery
• Gland Instance Segmentation Using Deep Multichannel Neural Networks
• Adversarial Example Detection for DNN Models: A Review and Experimental Comparison
• Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks
• Visual Identification of Individual Holstein-Friesian Cattle via Deep Metric Learning
• iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
• Hybrid Task Cascade for Instance Segmentation
• Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy
• Position Detection and Direction Prediction for Arbitrary-Oriented Ships via Multitask Rotation Region Convolutional Neural Network
• Deep-Learning-Based Image Segmentation Integrated with Optical Microscopy for Automatically Searching for Two-Dimensional Materials
• RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• TSM: Temporal Shift Module for Efficient Video Understanding
• Simultaneous Traffic Sign Detection and Boundary Estimation using Convolutional Neural Network
• DeeperLab: Single-Shot Image Parser
• CornerNet-Lite: Efficient Keypoint Based Object Detection
• Universal Domain Adaptation through Self Supervision
• Probabilistic two-stage detection
• From Handcrafted to Deep Features for Pedestrian Detection: A Survey
• Efficient DETR: Improving End-to-End Object Detector with Dense Prior
• Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton
• From Google Maps to a Fine-Grained Catalog of Street trees
• STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
• A Survey on Long-Tailed Visual Recognition
• Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing
• Context-Aware Visual Policy Network for Fine-Grained Image Captioning
• Deep Learning in Photoacoustic Tomography: Current approaches and future directions
• DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
• Audiovisual SlowFast Networks for Video Recognition
• BoxCars: Improving Fine-Grained Recognition of Vehicles using 3-D Bounding Boxes in Traffic Surveillance
• SegICP: Integrated Deep Semantic Segmentation and Pose Estimation
• Robust Spatial Filtering with Graph Convolutional Neural Networks
• Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar
• DPatch: An Adversarial Patch Attack on Object Detectors
• Multiscale Domain Adaptive YOLO for Cross-Domain Object Detection
• Bag of Freebies for Training Object Detection Neural Networks
• CornerNet: Detecting Objects as Paired Keypoints
• RepPoints: Point Set Representation for Object Detection
• Cascaded Region-based Densely Connected Network for Event Detection: A Seismic Application
• SlowFast Networks for Video Recognition
• Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning
• A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery
• CNN-based Density Estimation and Crowd Counting: A Survey
• UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking
• Toward Transformer-Based Object Detection
• A deep learning framework for quality assessment and restoration in video endoscopy
• Convolutional Oriented Boundaries
• MirrorNet: Bio-Inspired Camouflaged Object Segmentation
• Real-Time Fruit Recognition and Grasping Estimation for Autonomous Apple Harvesting
• Libra R-CNN: Towards Balanced Learning for Object Detection
• An All-in-One Network for Dehazing and Beyond
• Joint 3D Proposal Generation and Object Detection from View Aggregation
• Towards Accurate One-Stage Object Detection with AP-Loss
• Masked-attention Mask Transformer for Universal Image Segmentation
• Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
• Track to Reconstruct and Reconstruct to Track
• JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environments
• Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification
• Learning Dual Semantic Relations with Graph Attention for Image-Text Matching
• FastDeepIoT: Towards Understanding and Optimizing Neural Network Execution Time on Mobile and Embedded Devices
• Learning to detect chest radiographs containing lung nodules using visual attention networks
• Counting of Grapevine Berries in Images via Semantic Segmentation using Convolutional Neural Networks
• Scaled-YOLOv4: Scaling Cross Stage Partial Network
• ICNet for Real-Time Semantic Segmentation on High-Resolution Images
• Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
• Deep Learning for Logo Recognition
• Pix2seq: A Language Modeling Framework for Object Detection
• Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
• Drivers Drowsiness Detection using Condition-Adaptive Representation Learning Framework
• Incorporating User Micro-behaviors and Item Knowledge into Multi-task Learning for Session-based Recommendation
• Neural Networks for Entity Matching: A Survey
• TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
• Learning Multilayer Channel Features for Pedestrian Detection
• Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
• A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization
• Accelerating 3D Deep Learning with PyTorch3D
• Simple Online and Realtime Tracking with a Deep Association Metric
• Postdisaster image-based damage detection and repair cost estimation of reinforced concrete buildings using dual convolutional neural networks
• Rain rendering for evaluating and improving robustness to bad weather
• RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free
• Image coding for machines: an end-to-end learned approach
• Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey
• R${}^3$-Net: A Deep Network for Multi-oriented Vehicle Detection in Aerial Images and Videos
• Adapting Mask-RCNN for Automatic Nucleus Segmentation
• Image Augmentations for GAN Training
• Building Damage Detection in Satellite Imagery Using Convolutional Neural Networks
• Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training
• GhostNet: More Features from Cheap Operations
• A Comprehensive Study of Deep Video Action Recognition
• Recent Advances in Deep Learning: An Overview
• 3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents
• CLIP-Adapter: Better Vision-Language Models with Feature Adapters
• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• Multivariate Confidence Calibration for Object Detection
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks
• Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
• Rethinking on Multi-Stage Networks for Human Pose Estimation
• Multi-Scale Single Image Dehazing Using Laplacian and Gaussian Pyramids
• ByteTrack: Multi-Object Tracking by Associating Every Detection Box
• Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter
• Localizing Objects with Self-Supervised Transformers and no Labels
• Weakly-supervised DCNN for RGB-D Object Recognition in Real-World Applications Which Lack Large-scale Annotated Training Data
• You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
• Bottom-up Object Detection by Grouping Extreme and Center Points
• Training Convolutional Neural Networks with Limited Training Data for Ear Recognition in the Wild
• Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks
• Addressing Failure Prediction by Learning Model Confidence
• Zero-Shot Detection
• Incremental Object Detection via Meta-Learning
• Siamese Attentional Keypoint Network for High Performance Visual Tracking
• Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
• Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
• Semantics for Robotic Mapping, Perception and Interaction: A Survey
• An Empirical Study of Spatial Attention Mechanisms in Deep Networks
• Cascade R-CNN: High Quality Object Detection and Instance Segmentation
• PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images
• Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
• StarNet: Targeted Computation for Object Detection in Point Clouds
• Rearrangement: A Challenge for Embodied AI
• See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification
• Pose-Aware Instance Segmentation Framework from Cone Beam CT Images for Tooth Segmentation
• Rethinking and Designing a High-performing Automatic License Plate Recognition Approach
• From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network
• Video Salient Object Detection Using Spatiotemporal Deep Features
• End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds
• A Survey on Collaborative DNN Inference for Edge Intelligence
• AU R-CNN: Encoding Expert Prior Knowledge into R-CNN for Action Unit Detection
• Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
• Instance Segmentation in the Dark
• Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark
• Learning to Fuse Things and Stuff
• Focus: Querying Large Video Datasets with Low Latency and Low Cost
• Deep Ordinal Hashing with Spatial Attention
• Abnormal Colon Polyp Image Synthesis Using Conditional Adversarial Networks for Improved Detection Performance
• Next-Active-Object prediction from Egocentric Videos
• G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection
• Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
• Probabilistic and Geometric Depth: Detecting Objects in Perspective
• How Much Position Information Do Convolutional Neural Networks Encode?
• Universal Joint Feature Extraction for P300 EEG Classification using Multi-task Autoencoder
• Towards Automated Infographic Design: Deep Learning-based Auto-Extraction of Extensible Timeline
• Anomaly Detection in Traffic Scenes via Spatial-aware Motion Reconstruction
• PP-YOLOv2: A Practical Object Detector
• Self-supervised Image Enhancement Network: Training with Low Light Images Only
• Image Captioning: Transforming Objects into Words
• SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization
• Accelerator-Aware Pruning for Convolutional Neural Networks
• A Deep Journey into Super-resolution: A survey
• Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity
• Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation
• Segmentation of cell-level anomalies in electroluminescence images of photovoltaic modules
• Adversarial Attacks Against Deep Generative Models on Data: A Survey
• Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells
• Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
• An application of a deep learning algorithm for automatic detection of unexpected accidents under bad CCTV monitoring conditions in tunnels
• Arbitrary-Oriented Ship Detection through Center-Head Point Extraction
• On the Origin of Deep Learning
• Perceptual Generative Adversarial Networks for Small Object Detection
• Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localization
• A novel Region of Interest Extraction Layer for Instance Segmentation
• Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference
• RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks
• AP-Loss for Accurate One-Stage Object Detection
• Scale-Aware Trident Networks for Object Detection
• CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models
• Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
• Object Level Visual Reasoning in Videos
• A Deep Learning System That Generates Quantitative CT Reports for Diagnosing Pulmonary Tuberculosis
• Deep Image Retrieval: Learning global representations for image search
• High precision control and deep learning-based corn stand counting algorithms for agricultural robot
• A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
• 3D RoI-aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation
• Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars
• Stacked Deconvolutional Network for Semantic Segmentation
• What makes instance discrimination good for transfer learning?
• Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes
• Spatiotemporal Contrastive Video Representation Learning
• Deep Divergence-Based Approach to Clustering
• Exploring Randomly Wired Neural Networks for Image Recognition
• FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection
• Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures
• Advances and Applications of Computer Vision Techniques in Vehicle Trajectory Generation and Surrogate Traffic Safety Indicators
• Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
• Learning Rich Features for Image Manipulation Detection
• DirectPose: Direct End-to-End Multi-Person Pose Estimation
• Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning
• Deep Learning Techniques for In-Crop Weed Identification: A Review
• SAR Image Despeckling by Deep Neural Networks: from a pre-trained model to an end-to-end training strategy
• Online PCB Defect Detector On A New PCB Defect Dataset
• Occlusion Handling in Generic Object Detection: A Review
• Local Aggregation for Unsupervised Learning of Visual Embeddings
• Improving Transferability of Adversarial Examples with Input Diversity
• Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction
• Supervised Compression for Resource-Constrained Edge Computing Systems
• A Multi-Level Approach to Waste Object Segmentation
• Complex-YOLO: Real-time 3D Object Detection on Point Clouds
• InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Images
• HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
• IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection
• Multi-Class Multi-Object Tracking using Changing Point Detection
• Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction
• Enabling Pedestrian Safety using Computer Vision Techniques: A Case Study of the 2018 Uber Inc. Self-driving Car Crash
• Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
• AutoDNNchip: An Automated DNN Chip Predictor and Builder for Both FPGAs and ASICs
• Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning
• Handgun detection using combined human pose and weapon appearance
• Depth Adaptive Deep Neural Network for Semantic Segmentation
• MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?
• Traffic Light Recognition Using Deep Learning and Prior Maps for Autonomous Cars
• Learning Multi-Attention Context Graph for Group-Based Re-Identification
• Transferable Interactiveness Knowledge for Human-Object Interaction Detection
• Vehicle Tracking Using Surveillance with Multimodal Data Fusion
• Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection
• Towards seamless multi-view scene analysis from satellite to street-level
• A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects
• RepPoints V2: Verification Meets Regression for Object Detection
• Few-Shot Learning with Geometric Constraints
• Driver Action Prediction Using Deep (Bidirectional) Recurrent Neural Network
• Transfer Learning-based Road Damage Detection for Multiple Countries
• Artificial Neural Network Based Breast Cancer Screening: A Comprehensive Review
• Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
• BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding
• TinaFace: Strong but Simple Baseline for Face Detection
• Attention-guided Context Feature Pyramid Network for Object Detection
• Center-based 3D Object Detection and Tracking
• EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach
• Relation Networks for Object Detection
• Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering
• Self-EMD: Self-Supervised Object Detection without ImageNet
• Bilinear CNNs for Fine-grained Visual Recognition
• Optimizing Rank-based Metrics with Blackbox Differentiation
• A Study of Face Obfuscation in ImageNet
• RiFCN: Recurrent Network in Fully Convolutional Network for Semantic Segmentation of High Resolution Remote Sensing Images
• One-Shot Instance Segmentation
• Bayesian Loss for Crowd Count Estimation with Point Supervision
• Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
• End-to-End Video Instance Segmentation with Transformers
• Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
• HOI Analysis: Integrating and Decomposing Human-Object Interaction
• Face Detection Using Improved Faster RCNN
• Accelerating Flash Calculation through Deep Learning Methods
• Rethinking the Hyperparameters for Fine-tuning
• Learning Modulated Loss for Rotated Object Detection
• Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
• MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects
• Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
• Learning to Refine Object Segments
• SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network
• ASFormer: Transformer for Action Segmentation
• Deep Set Prediction Networks
• Neural Attention for Image Captioning: Review of Outstanding Methods
• Panoptic Feature Pyramid Networks
• Domain Adaptation for Object Detection via Style Consistency
• MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection
• Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets
• ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis
• Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
• Multi-modal Deep Analysis for Multimedia
• Damage detection using in-domain and cross-domain transfer learning
• Security and Privacy Issues in Deep Learning
• Cascaded Boundary Regression for Temporal Action Detection
• Region Proposal by Guided Anchoring
• Learning Human-Object Interactions by Graph Parsing Neural Networks
• One-Two-One Networks for Compression Artifacts Reduction in Remote Sensing
• Finding any Waldo: zero-shot invariant and efficient visual search
• Radar Voxel Fusion for 3D Object Detection
• Relation-Aware Graph Attention Network for Visual Question Answering
• Data Augmentation for Object Detection via Progressive and Selective Instance-Switching
• InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining
• Apple Counting using Convolutional Neural Networks
• SOLQ: Segmenting Objects by Learning Queries
• Multiscale Vision Transformers
• Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses
• Overcoming Small Minirhizotron Datasets Using Transfer Learning
• Privacy Protection in Street-View Panoramas using Depth and Multi-View Imagery
• Forecasting Action through Contact Representations from First Person Video
• Driving Scene Perception Network: Real-time Joint Detection, Depth Estimation and Semantic Segmentation
• i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
• Lightweight Modules for Efficient Deep Learning based Image Restoration
• Normalized Cut Loss for Weakly-supervised CNN Segmentation
• Pyramid Mask Text Detector
• BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
• Uncertainty for Identifying Open-Set Errors in Visual Object Detection
• Background Learnable Cascade for Zero-Shot Object Detection
• Deep Learning for Plasma Tomography and Disruption Prediction from Bolometer Data
• PixelLink: Detecting Scene Text via Instance Segmentation
• DEFT: Detection Embeddings for Tracking
• Soft Sampling for Robust Object Detection
• Tensor Programs II: Neural Tangent Kernel for Any Architecture
• SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization
• Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation
• Real Time Bangladeshi Sign Language Detection using Faster R-CNN
• STN-OCR: A single Neural Network for Text Detection and Text Recognition
• A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications
• Object DGCNN: 3D Object Detection using Dynamic Graphs
• Progressive Coordinate Transforms for Monocular 3D Object Detection
• Toward unsupervised, multi-object discovery in large-scale image collections
• Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
• Adversarial Examples in Modern Machine Learning: A Review
• On the Binding Problem in Artificial Neural Networks
• Simultaneously Localize, Segment and Rank the Camouflaged Objects
• 3D Object Proposals using Stereo Imagery for Accurate Object Class Detection
• Joint Monocular 3D Vehicle Detection and Tracking
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
• How convolutional neural network see the world - A survey of convolutional neural network visualization methods
• Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
• Reference-based Defect Detection Network
• Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors
• MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks
• Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling
• VideoMix: Rethinking Data Augmentation for Video Classification
• M6: A Chinese Multimodal Pretrainer
• Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
• CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation
• Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection
• Stacked Cross Attention for Image-Text Matching
• Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
• Spatio-Temporal Point Process for Multiple Object Tracking
• Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets
• Early Detection of Retinopathy of Prematurity stage using Deep Learning approach
• CenterNet3D: An Anchor Free Object Detector for Point Cloud
• ViDT: An Efficient and Effective Fully Transformer-based Object Detector
• Traffic-Aware Multi-Camera Tracking of Vehicles Based on ReID and Camera Link Model
• LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
• Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands
• Knowledge-Embedded Routing Network for Scene Graph Generation
• Visual Object Tracking in First Person Vision
• PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling
• Back to Simplicity: How to Train Accurate BNNs from Scratch?
• Distilling Object Detectors with Task Adaptive Regularization
• Detecting Multi-Oriented Text with Corner-based Region Proposals
• TNCR: Table Net Detection and Classification Dataset
• Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
• On the detection-to-track association for online multi-object tracking
• CARAFE: Content-Aware ReAssembly of FEatures
• Prime Sample Attention in Object Detection
• Defending Against Universal Attacks Through Selective Feature Regeneration
• Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection
• DeepIris: Iris Recognition Using A Deep Learning Approach
• Towards Unconstrained Palmprint Recognition on Consumer Devices: a Literature Review
• The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion
• Combination of Multiple Global Descriptors for Image Retrieval
• Visual Affordance and Function Understanding: A Survey
• Multi-Target Deep Learning for Algal Detection and Classification
• Object Detection for Comics using Manga109 Annotations
• Comprehensive Instructional Video Analysis: The COIN Dataset and Performance Evaluation
• LFFD: A Light and Fast Face Detector for Edge Devices
• AugFPN: Improving Multi-scale Feature Learning for Object Detection
• Tool Detection and Operative Skill Assessment in Surgical Videos Using Region-Based Convolutional Neural Networks
• CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
• Multi-Channel CNN-based Object Detection for Enhanced Situation Awareness
• S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networks
• Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
• DeLTA: GPU Performance Model for Deep Learning Applications with In-depth Memory System Traffic Analysis
• Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
• Hearing What You Cannot See: Acoustic Vehicle Detection Around Corners
• Multi-adversarial Faster-RCNN for Unrestricted Object Detection
• Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events
• Geometric Pose Affordance: 3D Human Pose with Scene Constraints
• Bounding Box Regression with Uncertainty for Accurate Object Detection
• Distilling Knowledge by Mimicking Features
• CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection
• Detection of 3D Bounding Boxes of Vehicles Using Perspective Transformation for Accurate Speed Measurement
• ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks
• SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking
• MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
• QueryProp: Object Query Propagation for High-Performance Video Object Detection
• Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks
• A Recurrent Vision-and-Language BERT for Navigation
• Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds
• PubLayNet: largest dataset ever for document layout analysis
• DADA: Differentiable Automatic Data Augmentation
• Dense Contrastive Learning for Self-Supervised Visual Pre-Training
• A Vision-based Social Distancing and Critical Density Detection System for COVID-19
• Improved training of binary networks for human pose estimation and image recognition
• FcaNet: Frequency Channel Attention Networks
• Online Structured Sparsity-based Moving Object Detection from Satellite Videos
• Physical Adversarial Attack on Vehicle Detector in the Carla Simulator
• AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling
• Unbiased Scene Graph Generation from Biased Training
• HAKE: Human Activity Knowledge Engine
• Single-shot 3D multi-person pose estimation in complex images
• ResizeMix: Mixing Data with Preserved Object Information and True Labels
• AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing
• Sequence Level Semantics Aggregation for Video Object Detection
• Anchor Cascade for Efficient Face Detection
• FingerNet: Pushing The Limits of Fingerprint Recognition Using Convolutional Neural Network
• Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking
• Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images
• Class-Difficulty Based Methods for Long-Tailed Visual Recognition
• FCOS: A simple and strong anchor-free object detector
• 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
• A Robust Illumination-Invariant Camera System for Agricultural Applications
• Graph-based Knowledge Distillation by Multi-head Attention Network
• Text-Based Person Search with Limited Data
• DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
• SOLO: Segmenting Objects by Locations
• CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputation
• Unifying Multimodal Transformer for Bi-directional Image and Text Generation
• Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
• Context Model for Pedestrian Intention Prediction using Factored Latent-Dynamic Conditional Random Fields
• Shape Robust Text Detection with Progressive Scale Expansion Network
• ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
• PyramidBox++: High Performance Detector for Finding Tiny Face
• Compositional Memory for Visual Question Answering
• WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
• Image-based table recognition: data, model, and evaluation
• Conditional Gaussian Distribution Learning for Open Set Recognition
• ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition
• Saccader: Improving Accuracy of Hard Attention Models for Vision
• Fast object detection in compressed JPEG Images
• RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
• Learning non-maximum suppression
• Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation
• Learning to Transfer Examples for Partial Domain Adaptation
• TensorMask: A Foundation for Dense Object Segmentation
• Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network
• Mask-Guided Attention Network for Occluded Pedestrian Detection
• UG${}^{2+}$ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments
• Dual-stream Network for Visual Recognition
• Distilling Object Detectors with Feature Richness
• EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
• Mining the Benefits of Two-stage and One-stage HOI Detection
• FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
• Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering
• Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Data
• SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection
• Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation
• Tracklets Predicting Based Adaptive Graph Tracking
• A Multimodal Memes Classification: A Survey and Open Research Issues
• CPS++: Improving Class-level 6D Pose and Shape Estimation From Monocular Images With Self-Supervised Learning
• CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving
• Objects detection for remote sensing images based on polar coordinates
• Learning Human-Object Interaction Detection using Interaction Points
• A Learning Framework for n-bit Quantized Neural Networks toward FPGAs
• P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding
• An original framework for Wheat Head Detection using Deep, Semi-supervised and Ensemble Learning within Global Wheat Head Detection (GWHD) Dataset
• Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
• Early Action Prediction with Generative Adversarial Networks
• Multimodal Unified Attention Networks for Vision-and-Language Interactions
• 6-DoF Object Pose from Semantic Keypoints
• EmbedMask: Embedding Coupling for One-stage Instance Segmentation
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• f-CNN${}^{\text{x}}$: A Toolflow for Mapping Multi-CNN Applications on FPGAs
• PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
• Training Binary Neural Networks through Learning with Noisy Supervision
• An Empirical Study on Leveraging Scene Graphs for Visual Question Answering
• Multi-Task Incremental Learning for Object Detection
• Data Extraction from Charts via Single Deep Neural Network
• Fast Visual Object Tracking with Rotated Bounding Boxes
• S${}^3$FD: Single Shot Scale-invariant Face Detector
• Exploring Self-attention for Image Recognition
• Hybrid Channel Based Pedestrian Detection
• AP-MTL: Attention Pruned Multi-task Learning Model for Real-time Instrument Detection and Segmentation in Robot-assisted Surgery
• End-to-End Incremental Learning
• Object Detection Networks on Convolutional Feature Maps
• Learning Independent Instance Maps for Crowd Localization
• Negative Margin Matters: Understanding Margin in Few-shot Classification
• Long-Term Feature Banks for Detailed Video Understanding
• Extending Maps with Semantic and Contextual Object Information for Robot Navigation: a Learning-Based Framework using Visual and Depth Cues
• Stroke-Based Scene Text Erasing Using Synthetic Data for Training
• Virtual to Real adaptation of Pedestrian Detectors
• VarifocalNet: An IoU-aware Dense Object Detector
• Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection
• Learning Spatiotemporal Features via Video and Text Pair Discrimination
• D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
• Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models
• Where are the Masks: Instance Segmentation with Image-level Supervision
• Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions
• SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving
• Deep Neural Network with l2-norm Unit for Brain Lesions Detection
• Classification based Grasp Detection using Spatial Transformer Network
• TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
• Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
• PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
• An embedded system for the automated generation of labeled plant images to enable machine learning applications in agriculture
• Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses
• Deep Texture-Aware Features for Camouflaged Object Detection
• Deep Co-supervision and Attention Fusion Strategy for Automatic COVID-19 Lung Infection Segmentation on CT Images
• Improved Selective Refinement Network for Face Detection
• Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
• Radar-Camera Sensor Fusion for Joint Object Detection and Distance Estimation in Autonomous Vehicles
• TableSense: Spreadsheet Table Detection with Convolutional Neural Networks
• Concurrent Activity Recognition with Multimodal CNN-LSTM Structure
• Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking
• Gradient Centralization: A New Optimization Technique for Deep Neural Networks
• MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
• Towards Real-Time Multi-Object Tracking
• DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning
• Sign Language Recognition via Skeleton-Aware Multi-Model Ensemble
• Benchmarking Single Image Dehazing and Beyond
• AIBench: An Industry Standard Internet Service AI Benchmark Suite
• Generation of microbial colonies dataset with deep learning style transfer
• Feature Fusion for Online Mutual Knowledge Distillation
• The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
• 3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds
• It Takes Two to Tango: Towards Theory of AI's Mind
• Exploring Object Relation in Mean Teacher for Cross-Domain Detection
• A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection
• Are we pretraining it right? Digging deeper into visio-linguistic pretraining
• C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
• SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
• Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
• Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network
• Learning Deep ResNet Blocks Sequentially using Boosting Theory
• VD-BERT: A Unified Vision and Dialog Transformer with BERT
• A Deep One-Shot Network for Query-based Logo Retrieval
• SIFT Meets CNN: A Decade Survey of Instance Retrieval
• Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
• Learning to Assemble Neural Module Tree Networks for Visual Grounding
• Video Action Understanding
• Multimodal Transformer with Multi-View Visual Representation for Image Captioning
• DeepBox: Learning Objectness with Convolutional Networks
• Scene Graph Generation with External Knowledge and Image Reconstruction
• Memory Enhanced Global-Local Aggregation for Video Object Detection
• Multiple Object Tracking by Flowing and Fusing
• Relation Distillation Networks for Video Object Detection
• TANet: Robust 3D Object Detection from Point Clouds with Triple Attention
• Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
• Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation
• Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
• CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
• Improving Auto-Augment via Augmentation-Wise Weight Sharing
• An Annotation Saved is an Annotation Earned: Using Fully Synthetic Training for Object Instance Detection
• SRG: Snippet Relatedness-based Temporal Action Proposal Generator
• MiniVLM: A Smaller and Faster Vision-Language Model
• CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence
• FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
• PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
• PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection
• FedVision: An Online Visual Object Detection Platform Powered by Federated Learning
• Efficient Bird Eye View Proposals for 3D Siamese Tracking
• Pillar-based Object Detection for Autonomous Driving
• Tracking Holistic Object Representations
• Age and Gender Prediction From Face Images Using Attentional Convolutional Network
• Scaling Wide Residual Networks for Panoptic Segmentation
• Simultaneous multi-view instance detection with learned geometric soft-constraints
• G-TAD: Sub-Graph Localization for Temporal Action Detection
• A Survey of Modern Object Detection Literature using Deep Learning
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog
• MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
• Improving Image Captioning with Better Use of Captions
• UFO: A UniFied TransfOrmer for Vision-Language Representation Learning
• One-shot Face Reenactment
• Exploring Categorical Regularization for Domain Adaptive Object Detection
• Universal Adversarial Perturbations: A Survey
• WIDER Face and Pedestrian Challenge 2018: Methods and Results
• BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics
• Large-Scale Generative Data-Free Distillation
• Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations
• Dynamic Adversarial Patch for Evading Object Detection Models
• Decoupled Adaptation for Cross-Domain Object Detection
• Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
• The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes
• FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
• Spatial-Temporal Relation Networks for Multi-Object Tracking
• On Feature Normalization and Data Augmentation
• Chainer: A Deep Learning Framework for Accelerating the Research Cycle
• InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting
• FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking
• Language-Conditioned Graph Networks for Relational Reasoning
• MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision
• Improving Object Detection from Scratch via Gated Feature Reuse
• Towards a Robust Deep Neural Network in Texts: A Survey
• Simple Training Strategies and Model Scaling for Object Detection
• Light-Weight RetinaNet for Object Detection
• Cell Detection in Microscopy Images with Deep Convolutional Neural Network and Compressed Sensing
• Weakly Supervised Dense Video Captioning
• Reduced Focal Loss: 1st Place Solution to xView object detection in Satellite Imagery
• Forward and Backward Information Retention for Accurate Binary Neural Networks
• A benchmark dataset for deep learning-based airplane detection: HRPlanes
• Conditional Convolutions for Instance Segmentation
• AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection
• Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systems
• Image Amodal Completion: A Survey
• Learning Multi-level Deep Representations for Image Emotion Classification
• Deep Co-Training for Semi-Supervised Image Recognition
• A Survey on Deep Learning Toolkits and Libraries for Intelligent User Interfaces
• Unpaired Image Captioning via Scene Graph Alignments
• A Survey of Deep Learning Approaches for OCR and Document Understanding
• Normalized and Geometry-Aware Self-Attention Network for Image Captioning
• VID-WIN: Fast Video Event Matching with Query-Aware Windowing at the Edge for the Internet of Multimedia Things
• Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization
• Text Detection and Recognition in the Wild: A Review
• Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation
• Distilling Object Detectors via Decoupled Features
• YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design
• HARRISON: A Benchmark on HAshtag Recommendation for Real-world Images in Social Networks
• Fourier Contour Embedding for Arbitrary-Shaped Text Detection
• 3D Point Cloud Descriptors in Hand-crafted and Deep Learning Age: State-of-the-Art
• DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors
• Rethinking "Batch" in BatchNorm
• Exploring Data Augmentation for Multi-Modality 3D Object Detection
• Preferences Prediction using a Gallery of Mobile Device based on Scene Recognition and Object Detection
• End-to-end Flow Correlation Tracking with Spatial-temporal Attention
• Deep Neural Networks for Marine Debris Detection in Sonar Images
• Single-Stage Multi-Person Pose Machines
• Progressive Sparse Local Attention for Video object detection
• e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
• Understanding the Behaviour of Contrastive Loss
• Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
• Computing Systems for Autonomous Driving: State-of-the-Art and Challenges
• DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
• Direction Concentration Learning: Enhancing Congruency in Machine Learning
• Restoring Negative Information in Few-Shot Object Detection
• Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection
• A Performance Comparison of Loss Functions for Deep Face Recognition
• Objectness Scoring and Detection Proposals in Forward-Looking Sonar Images with Convolutional Neural Networks
• Corner Proposal Network for Anchor-free, Two-stage Object Detection
• LAEO-Net++: revisiting people Looking At Each Other in videos
• Recent Advances in Deep Learning for Object Detection
• Autonomous and cooperative design of the monitor positions for a team of UAVs to maximize the quantity and quality of detected objects
• Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
• Involution: Inverting the Inherence of Convolution for Visual Recognition
• Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review
• Attention Based Glaucoma Detection: A Large-scale Database and CNN Model
• Zoom Out-and-In Network with Recursive Training for Object Proposal
• MITOS-RCNN: A Novel Approach to Mitotic Figure Detection in Breast Cancer Histopathology Images using Region Based Convolutional Neural Networks
• How To Train Your Deep Multi-Object Tracker
• CSL-YOLO: A New Lightweight Object Detection System for Edge Computing
• Deep Contextual Attention for Human-Object Interaction Detection
• An explainable deep vision system for animal classification and detection in trail-camera images with automatic post-deployment retraining
• Dynamic Anchor Learning for Arbitrary-Oriented Object Detection
• Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments
• PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
• Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
• Revisiting Locally Supervised Learning: an Alternative to End-to-end Training
• Attention-guided Unified Network for Panoptic Segmentation
• The More You Know: Using Knowledge Graphs for Image Classification
• GradAug: A New Regularization Method for Deep Neural Networks
• Domain Adaptation without Source Data
• Multi-Object Tracking with Siamese Track-RCNN
• SA-Net: Deep Neural Network for Robot Trajectory Recognition from RGB-D Streams
• From Human Mesenchymal Stromal Cells to Osteosarcoma Cells Classification by Deep Learning
• Detection in Crowded Scenes: One Proposal, Multiple Predictions
• Spatially Adaptive Computation Time for Residual Networks
• Spatio-Temporal Attention Models for Grounded Video Captioning
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
• GoDP: Globally optimized dual pathway system for facial landmark localization in-the-wild
• Adaptive NMS: Refining Pedestrian Detection in a Crowd
• Dual-Level Collaborative Transformer for Image Captioning
• Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation
• Person Search via A Mask-Guided Two-Stream CNN Model
• Crafting GBD-Net for Object Detection
• PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices
• Towards Balanced Learning for Instance Recognition
• Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
• Equalization Loss for Long-Tailed Object Recognition
• X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
• Extended Feature Pyramid Network for Small Object Detection
• X-volution: On the unification of convolution and self-attention
• Mixing Real and Synthetic Data to Enhance Neural Network Training -- A Review of Current Approaches
• DP-Image: Differential Privacy for Image Data in Feature Space
• AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph
• Harmonizing Transferability and Discriminability for Adapting Object Detectors
• Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring
• Locally Free Weight Sharing for Network Width Search
• Disentangling Label Distribution for Long-tailed Visual Recognition
• ConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks
• Regularizing Deep Networks with Semantic Data Augmentation
• Towards Unconstrained End-to-End Text Spotting
• Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts
• NAS-FCOS: Fast Neural Architecture Search for Object Detection
• Image Segmentation via Probabilistic Graph Matching
• A Light Dual-Task Neural Network for Haze Removal
• Video action detection by learning graph-based spatio-temporal interactions
• Fixing the train-test resolution discrepancy
• Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
• Learning the Best Pooling Strategy for Visual Semantic Embedding
• Simple Unsupervised Multi-Object Tracking
• Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
• Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels
• Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations
• Visual Semantic Reasoning for Image-Text Matching
• Context-Driven Detection of Invertebrate Species in Deep-Sea Video
• Training Deep Learning Based Denoisers without Ground Truth Data
• Automated System for Ship Detection from Medium Resolution Satellite Optical Imagery
• Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs
• EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching
• Deep Learning for Scene Classification: A Survey
• Towards Compact and Robust Deep Neural Networks
• An End-to-End Network for Panoptic Segmentation
• Transformer-Based Source-Free Domain Adaptation
• Multi-Person Pose Estimation with Local Joint-to-Person Associations
• Pointly-Supervised Action Localization
• Active and Incremental Learning with Weak Supervision
• SIXray : A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images
• Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction
• A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension
• Language-Conditioned Imitation Learning for Robot Manipulation Tasks
• Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
• A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
• QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
• Multimodal Integration of Human-Like Attention in Visual Question Answering
• ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
• Pneumothorax Segmentation: Deep Learning Image Segmentation to predict Pneumothorax
• Embodied Visual Recognition
• Attentional Network for Visual Object Detection
• Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
• MOPT: Multi-Object Panoptic Tracking
• Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learning
• 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
• ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
• Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction
• Dog Identification using Soft Biometrics and Neural Networks
• Focal and Global Knowledge Distillation for Detectors
• An Accurate and Real-time Self-blast Glass Insulator Location Method Based On Faster R-CNN and U-net with Aerial Images
• Adapting Object Detectors with Conditional Domain Normalization
• Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
• Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes
• Knowledge driven Description Synthesis for Floor Plan Interpretation
• Side-Aware Boundary Localization for More Precise Object Detection
• Backdoor Attack through Frequency Domain
• Sequential Context Encoding for Duplicate Removal
• SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels
• CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
• Tackling the Unannotated: Scene Graph Generation with Bias-Reduced Models
• Masked Vision-Language Transformer in Fashion
• Deep Perceptual Compression
• Towards Unified INT8 Training for Convolutional Neural Network
• Quantifying Legibility of Indoor Spaces Using Deep Convolutional Neural Networks: Case Studies in Train Stations
• SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
• Language and Visual Entity Relationship Graph for Agent Navigation
• From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality
• Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling
• Co-localization with Category-Consistent Features and Geodesic Distance Propagation
• Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries
• Exploring Low-light Object Detection Techniques
• Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
• DFUC2020: Analysis Towards Diabetic Foot Ulcer Detection
• Certified Data Removal from Machine Learning Models
• Lightweight Convolutional Neural Network with Gaussian-based Grasping Representation for Robotic Grasping Detection
• A Scale Invariant Flatness Measure for Deep Network Minima
• PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN
• Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions
• Pose-adaptive Hierarchical Attention Network for Facial Expression Recognition
• A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
• Implicit Feature Pyramid Network for Object Detection
• TAP: Text-Aware Pre-training for Text-VQA and Text-Caption
• Counterfactual Critic Multi-Agent Training for Scene Graph Generation
• A survey of Object Classification and Detection based on 2D/3D data
• GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization
• Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019
• DRG: Dual Relation Graph for Human-Object Interaction Detection
• Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning
• Detecting Text in Natural Image with Connectionist Text Proposal Network
• WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection
• 3D Interpreter Networks for Viewer-Centered Wireframe Modeling
• Learning Object Relation Graph and Tentative Policy for Visual Navigation
• Cost Volume Pyramid Based Depth Inference for Multi-View Stereo
• Task-Aware Variational Adversarial Active Learning
• Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
• Deep Learning at 15PF: Supervised and Semi-Supervised Classification for Scientific Data
• CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
• Conservation AI: Live Stream Analysis for the Detection of Endangered Species Using Convolutional Neural Networks and Drone Technology
• Empirical Upper Bound in Object Detection and More
• Consistent Optimization for Single-Shot Object Detection
• Neural Person Search Machines
• ReenactGAN: Learning to Reenact Faces via Boundary Transfer
• Classification of Findings with Localized Lesions in Fundoscopic Images using a Regionally Guided CNN
• Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network
• Quasi-Dense Similarity Learning for Multiple Object Tracking
• Cross-domain Detection via Graph-induced Prototype Alignment
• Tracking Objects as Points
• Learning to decompose for object detection and instance segmentation
• Self-supervised learning for autonomous vehicles perception: A conciliation between analytical and learning methods
• ResNet or DenseNet? Introducing Dense Shortcuts to ResNet
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection
• Stories for Images-in-Sequence by using Visual and Narrative Components
• Contrastive Visual-Linguistic Pretraining
• C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
• Visual Parser: Representing Part-whole Hierarchies with Transformers
• Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation
• SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud
• A Delay Metric for Video Object Detection: What Average Precision Fails to Tell
• Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection
• Target Detection, Tracking and Avoidance System for Low-cost UAVs using AI-Based Approaches
• Joint Detection and Tracking in Videos with Identification Features
• One-Shot Object Detection without Fine-Tuning
• Bridging Knowledge Graphs to Generate Scene Graphs
• In Defense of Grid Features for Visual Question Answering
• UPSNet: A Unified Panoptic Segmentation Network
• Joint Iris Segmentation and Localization Using Deep Multi-task Learning Framework
• Learning to Collocate Neural Modules for Image Captioning
• Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
• Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
• Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
• Bridge Damage Detection using a Single-Stage Detector and Field Inspection Images
• Dual Refinement Feature Pyramid Networks for Object Detection
• The Next Big Thing(s) in Unsupervised Machine Learning: Five Lessons from Infant Learning
• Hierarchical LSTMs with Adaptive Attention for Visual Captioning
• QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information
• PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments
• Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA
• TDAPNet: Prototype Network with Recurrent Top-Down Attention for Robust Object Classification under Partial Occlusion
• SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking
• An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
• Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
• SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud
• Comparison Network for One-Shot Conditional Object Detection
• Person-in-WiFi: Fine-grained Person Perception using WiFi
• Siamese Box Adaptive Network for Visual Tracking
• Boundary Proposal Network for Two-Stage Natural Language Video Localization
• Large Scale Visual Food Recognition
• DeepWriter: A Multi-Stream Deep CNN for Text-independent Writer Identification
• Detailed 2D-3D Joint Representation for Human-Object Interaction
• Deep Optics for Monocular Depth Estimation and 3D Object Detection
• Multimodal Contrastive Training for Visual Representation Learning
• Temporal Recurrent Networks for Online Action Detection
• Revisiting Image-Language Networks for Open-ended Phrase Detection
• Two-Level Residual Distillation based Triple Network for Incremental Object Detection
• Cooperating RPN's Improve Few-Shot Object Detection
• Human-Object Interaction Prediction in Videos through Gaze Following
• Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction
• DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
• Universally Slimmable Networks and Improved Training Techniques
• From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning
• A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction
• Object-Based Visual Camera Pose Estimation From Ellipsoidal Model and 3D-Aware Ellipse Prediction
• Self-supervised Pre-training with Hard Examples Improves Visual Representations
• Object-aware Contrastive Learning for Debiased Scene Representation
• Saliency-Guided Attention Network for Image-Sentence Matching
• MotorEase: Automated Detection of Motor Impairment Accessibility Issues in Mobile App UIs
• Keep it Simple: Image Statistics Matching for Domain Adaptation
• Artificial and beneficial -- Exploiting artificial images for aerial vehicle detection
• $c^{+}$GAN: Complementary Fashion Item Recommendation
• SEIGAN: Towards Compositional Image Generation by Simultaneously Learning to Segment, Enhance, and Inpaint
• Sperm Detection and Tracking in Phase-Contrast Microscopy Image Sequences using Deep Learning and Modified CSR-DCF
• TOOD: Task-aligned One-stage Object Detection
• Interact as You Intend: Intention-Driven Human-Object Interaction Detection
• Imperceptible Adversarial Examples by Spatial Chroma-Shift
• Ocean: Object-aware Anchor-free Tracking
• CentripetalText: An Efficient Text Instance Representation for Scene Text Detection
• MOTR: End-to-End Multiple-Object Tracking with Transformer
• Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
• Structured Knowledge Distillation for Dense Prediction
• PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things
• Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
• Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
• Signet Ring Cell Detection With a Semi-supervised Learning Framework
• Cross-dataset Training for Class Increasing Object Detection
• Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems
• Online Object-Oriented Semantic Mapping and Map Updating
• Multi-Scale Attention Network for Crowd Counting
• Stabilized Medical Image Attacks
• Post-Training Piecewise Linear Quantization for Deep Neural Networks
• Target Driven Instance Detection
• Cross-view Relation Networks for Mammogram Mass Detection
• ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation
• Visual Concepts and Compositional Voting
• HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Faces
• VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning
• Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
• A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learning
• Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity
• RoIMix: Proposal-Fusion among Multiple Images for Underwater Object Detection
• Kernel Transformer Networks for Compact Spherical Convolution
• Dense RepPoints: Representing Visual Objects with Dense Point Sets
• Learning in the Frequency Domain
• RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation
• Structured Multimodal Attentions for TextVQA
• Adaptive Object Detection Using Adjacency and Zoom Prediction
• Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
• Self-Knowledge Distillation with Progressive Refinement of Targets
• Learning Temporal Pose Estimation from Sparsely-Labeled Videos
• CTAP: Complementary Temporal Action Proposal Generation
• Query-guided End-to-End Person Search
• Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation
• Align Deep Features for Oriented Object Detection
• Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation
• Deep Reasoning with Knowledge Graph for Social Relationship Understanding
• Objects in Semantic Topology
• BorderDet: Border Feature for Dense Object Detection
• Real-Time Seamless Single Shot 6D Object Pose Prediction
• Deeply Explain CNN via Hierarchical Decomposition
• CenterFace: Joint Face Detection and Alignment Using Face as Point
• Arbitrary-Shaped Text Detection withAdaptive Text Region Representation
• MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond
• MVOR: A Multi-view RGB-D Operating Room Dataset for 2D and 3D Human Pose Estimation
• Towards Noise-resistant Object Detection with Noisy Annotations
• A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion
• RetinaTrack: Online Single Stage Joint Detection and Tracking
• GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
• Shape or Texture: Understanding Discriminative Features in CNNs
• Deep traffic light detection by overlaying synthetic context on arbitrary natural images
• ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
• Addressing the Cold-Start Problem in Outfit Recommendation Using Visual Preference Modelling
• Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation
• Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning
• Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
• Contextual Multi-Scale Region Convolutional 3D Network for Activity Detection
• MoBiNet: A Mobile Binary Network for Image Classification
• Probabilistic Semantic Retrieval for Surveillance Videos with Activity Graphs
• Episode-based Prototype Generating Network for Zero-Shot Learning
• SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition
• Tracking by Instance Detection: A Meta-Learning Approach
• Cascaded Structure Tensor Framework for Robust Identification of Heavily Occluded Baggage Items from X-ray Scans
• Deep learning-based prediction of response to HER2-targeted neoadjuvant chemotherapy from pre-treatment dynamic breast MRI: A multi-institutional validation study
• Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
• BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision
• Benchmarking Deep Trackers on Aerial Videos
• MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding
• Segmentation is All You Need
• Looking in the Right place for Anomalies: Explainable AI through Automatic Location Learning
• Recurrent Autoregressive Networks for Online Multi-Object Tracking
• Robust Deep Neural Object Detection and Segmentation for Automotive Driving Scenario with Compressed Image Data
• A Cost-Effective Person-Following System for Assistive Unmanned Vehicles with Deep Learning at the Edge
• BoLTVOS: Box-Level Tracking for Video Object Segmentation
• Linguistically-aware Attention for Reducing the Semantic-Gap in Vision-Language Tasks
• Attention Neural Network for Trash Detection on Water Channels
• Dynamic Relevance Learning for Few-Shot Object Detection
• Deep Watershed Detector for Music Object Recognition
• Motion-Appearance Interactive Encoding for Object Segmentation in Unconstrained Videos
• Clustered Object Detection in Aerial Images
• DASS: Differentiable Architecture Search for Sparse neural networks
• Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation
• Accurate RGB-D Salient Object Detection via Collaborative Learning
• Comprehensive Image Captioning via Scene Graph Decomposition
• Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale
• Detecting Human-Object Interactions with Action Co-occurrence Priors
• Universal Semi-Supervised Semantic Segmentation
• Transfer Learning for Instance Segmentation of Waste Bottles using Mask R-CNN Algorithm
• SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
• WebVision Challenge: Visual Learning and Understanding With Web Data
• Self-supervised 6D Object Pose Estimation for Robot Manipulation
• Deep GrabCut for Object Selection
• OVANet: One-vs-All Network for Universal Domain Adaptation
• Actor-Centric Relation Network
• A Comparative Review of Recent Few-Shot Object Detection Algorithms
• COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis
• Learning Efficient Detector with Semi-supervised Adaptive Distillation
• IoU-aware Single-stage Object Detector for Accurate Localization
• VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning
• Counting and Segmenting Sorghum Heads
• Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector
• Wasserstein Distance Based Domain Adaptation for Object Detection
• Move to See Better: Self-Improving Embodied Object Detection
• End-to-End Object Detection with Fully Convolutional Network
• Memory Warps for Learning Long-Term Online Video Representations
• Person Recognition in Personal Photo Collections
• Human-centric Spatio-Temporal Video Grounding With Visual Transformers
• Generalization Bounds for Convolutional Neural Networks
• ASFD: Automatic and Scalable Face Detector
• Feature Intertwiner for Object Detection
• Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
• Rethinking Channel Dimensions for Efficient Model Design
• Structure-Aware Completion of Photogrammetric Meshes in Urban Road Environment
• Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
• Video Instance Segmentation
• Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
• When Healthcare Meets Off-the-Shelf WiFi: A Non-Wearable and Low-Costs Approach for In-Home Monitoring
• SWIPENET: Object detection in noisy underwater images
• Visual Object Recognition in Indoor Environments Using Topologically Persistent Features
• Hateful Memes Detection via Complementary Visual and Linguistic Networks
• Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
• HRCenterNet: An Anchorless Approach to Chinese Character Segmentation in Historical Documents
• A Configurable BNN ASIC using a Network of Programmable Threshold Logic Standard Cells
• AdderNet: Do We Really Need Multiplications in Deep Learning?
• Dynamic Refinement Network for Oriented and Densely Packed Object Detection
• Cross-Modal Graph with Meta Concepts for Video Captioning
• Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
• Pipelines for Procedural Information Extraction from Scientific Literature: Towards Recipes using Machine Learning and Data Science
• An Analysis of Scale Invariance in Object Detection - SNIP
• SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors
• Pose2Seg: Detection Free Human Instance Segmentation
• A Fast Face Detection Method via Convolutional Neural Network
• MovieNet: A Holistic Dataset for Movie Understanding
• Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning
• HPC AI500: The Methodology, Tools, Roofline Performance Models, and Metrics for Benchmarking HPC AI Systems
• IA-MOT: Instance-Aware Multi-Object Tracking with Motion Consistency
• MaskFace: multi-task face and landmark detector
• Train in Germany, Test in The USA: Making 3D Object Detectors Generalize
• Visual Relationship Detection using Scene Graphs: A Survey
• WQT and DG-YOLO: towards domain generalization in underwater object detection
• Modeling Visual Context is Key to Augmenting Object Detection Datasets
• TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems
• SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation
• Convolutional Recurrent Predictor: Implicit Representation for Multi-target Filtering and Tracking
• KeepAugment: A Simple Information-Preserving Data Augmentation Approach
• Slender Object Detection: Diagnoses and Improvements
• Learning Transferable Adversarial Examples via Ghost Networks
• SPLAT: Semantic Pixel-Level Adaptation Transforms for Detection
• Pose Estimation for Non-Cooperative Rendezvous Using Neural Networks
• AM-LFS: AutoML for Loss Function Search
• Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs
• NeRF in detail: Learning to sample for view synthesis
• Amodal Instance Segmentation
• Attribute Aware Pooling for Pedestrian Attribute Recognition
• Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos
• Instance Segmentation with Point Supervision
• AD-Det: Boosting Object Detection in UAV Images with Focused Small Objects and Balanced Tail Classes
• Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation
• Synthetic Document Generator for Annotation-free Layout Recognition
• Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation
• Online Object Representations with Contrastive Learning
• PolyTransform: Deep Polygon Transformer for Instance Segmentation
• Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid
• Class-Incremental Few-Shot Object Detection
• PASS3D: Precise and Accelerated Semantic Segmentation for 3D Point Cloud
• Machine-learning based methodologies for 3d x-ray measurement, characterization and optimization for buried structures in advanced ic packages
• Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes
• Accurate 6D Object Pose Estimation by Pose Conditioned Mesh Reconstruction
• Track to Detect and Segment: An Online Multi-Object Tracker
• Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview
• Let's measure run time! Extending the IR replicability infrastructure to include performance aspects
• Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions
• MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
• Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
• Soft Anchor-Point Object Detection
• Making History Matter: History-Advantage Sequence Training for Visual Dialog
• Breast Mass Detection with Faster R-CNN: On the Feasibility of Learning from Noisy Annotations
• ClipCap: CLIP Prefix for Image Captioning
• Concurrent Segmentation and Object Detection CNNs for Aircraft Detection and Identification in Satellite Images
• FBNetV5: Neural Architecture Search for Multiple Tasks in One Run
• Visual Compositional Learning for Human-Object Interaction Detection
• Feature Pyramid Grids
• More Grounded Image Captioning by Distilling Image-Text Matching Model
• Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
• Semi-supervised Open-World Object Detection
• Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments
• VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
• Fully Convolutional Networks for Panoptic Segmentation
• Point Cloud Instance Segmentation using Probabilistic Embeddings
• The NAO Backpack: An Open-hardware Add-on for Fast Software Development with the NAO Robot
• Emotion Recognition From Gait Analyses: Current Research and Future Directions
• Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers
• Beef Cattle Instance Segmentation Using Fully Convolutional Neural Network
• Convolutional Auto-encoding of Sentence Topics for Image Paragraph Generation
• Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection
• Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up
• Image-based localization using LSTMs for structured feature correlation
• A Dataset for Provident Vehicle Detection at Night
• Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning
• A 2D laser rangefinder scans dataset of standard EUR pallets
• Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
• Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech
• Appearance-Preserving 3D Convolution for Video-based Person Re-identification
• A Deep Learning-based Framework for the Detection of Schools of Herring in Echograms
• Learning a Layout Transfer Network for Context Aware Object Detection
• Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
• Pose Neural Fabrics Search
• Inter-Image Communication for Weakly Supervised Localization
• TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
• 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
• Towards Linking the Lakh and IMSLP Datasets
• Progressive Localization Networks for Language-based Moment Localization
• Online Multiple Pedestrians Tracking using Deep Temporal Appearance Matching Association
• Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation
• Dual Attention Networks for Visual Reference Resolution in Visual Dialog
• Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Clouds
• AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation
• On Learning Vehicle Detection in Satellite Video
• Analysis of diversity-accuracy tradeoff in image captioning
• CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection
• Rethinking Differentiable Search for Mixed-Precision Neural Networks
• Towards Compact ConvNets via Structure-Sparsity Regularized Filter Pruning
• Temporal HeartNet: Towards Human-Level Automatic Analysis of Fetal Cardiac Screening Video
• Exploiting long-term temporal dynamics for video captioning
• PaStaNet: Toward Human Activity Knowledge Engine
• An Analysis of Deep Object Detectors For Diver Detection
• The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
• Attentive Relational Networks for Mapping Images to Scene Graphs
• Guided Attention Network for Object Detection and Counting on Drones
• A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
• StartNet: Online Detection of Action Start in Untrimmed Videos
• VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
• Tracking objects using 3D object proposals
• Meta Module Network for Compositional Visual Reasoning
• Joint Contrastive Learning with Infinite Possibilities
• ScanSSD: Scanning Single Shot Detector for Mathematical Formulas in PDF Document Images
• AI Matrix: A Deep Learning Benchmark for Alibaba Data Centers
• A Software Architecture for Autonomous Vehicles: Team LRM-B Entry in the First CARLA Autonomous Driving Challenge
• Refinements in Motion and Appearance for Online Multi-Object Tracking
• CGaP: Continuous Growth and Pruning for Efficient Deep Learning
• HRank: Filter Pruning using High-Rank Feature Map
• Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification
• Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning
• Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization
• Reformulating HOI Detection as Adaptive Set Prediction
• Geometry Normalization Networks for Accurate Scene Text Detection
• Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters
• HiFT: Hierarchical Feature Transformer for Aerial Tracking
• Autonomous Marine Sampling Enhanced by Strategically Deployed Drifters in Marine Flow Fields
• Deep Frequent Spatial Temporal Learning for Face Anti-Spoofing
• DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling
• Fast Video Shot Transition Localization with Deep Structured Models
• Abstractive Text Classification Using Sequence-to-convolution Neural Networks
• Hallucination Improves Few-Shot Object Detection
• Detecting Noteheads in Handwritten Scores with ConvNets and Bounding Box Regression
• Self-Adversarial Disentangling for Specific Domain Adaptation
• How benign is benign overfitting?
• The Role of Context Selection in Object Detection
• Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-Time
• Fusion of Head and Full-Body Detectors for Multi-Object Tracking
• Attention Allocation Aid for Visual Search
• Generative Partition Networks for Multi-Person Pose Estimation
• Training a Fast Object Detector for LiDAR Range Images Using Labeled Data from Sensors with Higher Resolution
• Siamese Keypoint Prediction Network for Visual Object Tracking
• Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval
• Deep Affinity Net: Instance Segmentation via Affinity
• SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
• Learning Video Representations from Correspondence Proposals
• VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering
• Single Pixel Reconstruction for One-stage Instance Segmentation
• Automated Steel Bar Counting and Center Localization with Convolutional Neural Networks
• Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks
• Multiview Detection with Feature Perspective Transformation
• An End-to-End Network for Co-Saliency Detection in One Single Image
• Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation
• Affinity LCFCN: Learning to Segment Fish with Weak Supervision
• CO2: Consistent Contrast for Unsupervised Visual Representation Learning
• MFPN: A Novel Mixture Feature Pyramid Network of Multiple Architectures for Object Detection
• Down to the Last Detail: Virtual Try-on with Detail Carving
• Double Anchor R-CNN for Human Detection in a Crowd
• Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking
• Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
• X-Linear Attention Networks for Image Captioning
• Spatially Consistent Representation Learning
• Real-Time Shape Tracking of Facial Landmarks
• Co-Separating Sounds of Visual Objects
• PanoNet: Real-time Panoptic Segmentation through Position-Sensitive Feature Embedding
• An End-to-End Approach for Recognition of Modern and Historical Handwritten Numeral Strings
• OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network
• Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards
• Sex Trafficking Detection with Ordinal Regression Neural Networks
• Deep neural networks approach to microbial colony detection -- a comparative analysis
• 3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimation
• Lightweight Pyramid Networks for Image Deraining
• Sparse Weight Activation Training
• Prediction-Tracking-Segmentation
• MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering
• Rethinking Self-Supervised Learning: Small is Beautiful
• Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose
• VQA-LOL: Visual Question Answering under the Lens of Logic
• Learning Region Features for Object Detection
• NASGEM: Neural Architecture Search via Graph Embedding Method
• Open Set Recognition with Conditional Probabilistic Generative Models
• Advances in Deep Learning for Hyperspectral Image Analysis--Addressing Challenges Arising in Practical Imaging Scenarios
• Sketching Image Gist: Human-Mimetic Hierarchical Scene Graph Generation
• End-to-End Wireframe Parsing
• A Hybrid Approach and Unified Framework for Bibliographic Reference Extraction
• Sitatapatra: Blocking the Transfer of Adversarial Samples
• Learning from Lexical Perturbations for Consistent Visual Question Answering
• OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Learning Where to Focus for Efficient Video Object Detection
• 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection
• MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
• A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks
• Object-Centric Diagnosis of Visual Reasoning
• Toward Automatic Threat Recognition for Airport X-ray Baggage Screening with Deep Convolutional Object Detection
• Mask R-CNN with Pyramid Attention Network for Scene Text Detection
• Localizing Actions from Video Labels and Pseudo-Annotations
• SpatialFlow: Bridging All Tasks for Panoptic Segmentation
• AutoCaption: Image Captioning with Neural Architecture Search
• VIOLIN: A Large-Scale Dataset for Video-and-Language Inference
• MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos
• MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
• Table Structure Recognition using Top-Down and Bottom-Up Cues
• Plumber: Diagnosing and Removing Performance Bottlenecks in Machine Learning Data Pipelines
• Large-Scale Classification of Structured Objects using a CRF with Deep Class Embedding
• Harvesting, Detecting, and Characterizing Liver Lesions from Large-scale Multi-phase CT Data via Deep Dynamic Texture Learning
• SMOT: Single-Shot Multi Object Tracking
• Towards Phytoplankton Parasite Detection Using Autoencoders
• BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weights
• Road Damage Detection and Classification with Detectron2 and Faster R-CNN
• Revisiting the Sibling Head in Object Detector
• Localization in the Crowd with Topological Constraints
• Predicting Electricity Consumption using Deep Recurrent Neural Networks
• MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
• MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps
• Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training
• Combating Uncertainty with Novel Losses for Automatic Left Atrium Segmentation
• Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents
• Progressive Correspondence Pruning by Consensus Learning
• Dual-Awareness Attention for Few-Shot Object Detection
• Stacked Cross-modal Feature Consolidation Attention Networks for Image Captioning
• DR Loss: Improving Object Detection by Distributional Ranking
• Attention: A Big Surprise for Cross-Domain Person Re-Identification
• EXSCLAIM! -- An automated pipeline for the construction of labeled materials imaging datasets from literature
• Learning Pairwise Relationship for Multi-object Detection in Crowded Scenes
• VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data
• Point in, Box out: Beyond Counting Persons in Crowds
• Fine-Grained Image Analysis with Deep Learning: A Survey
• A Gap-Based Framework for Chinese Word Segmentation via Very Deep Convolutional Networks
• Diversifying Sample Generation for Accurate Data-Free Quantization
• NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentation
• Rethinking Classification and Localization for Cascade R-CNN
• LogoDet-3K: A Large-Scale Image Dataset for Logo Detection
• Rethinking Pseudo-LiDAR Representation
• Pose-based Modular Network for Human-Object Interaction Detection
• Driver Behavior Analysis Using Lane Departure Detection Under Challenging Conditions
• Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
• Unsupervised Hard Example Mining from Videos for Improved Object Detection
• Co-training for Deep Object Detection: Comparing Single-modal and Multi-modal Approaches
• GPS-Net: Graph Property Sensing Network for Scene Graph Generation
• STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction
• Improving Calibration for Long-Tailed Recognition
• Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning
• Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
• End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
• Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning
• Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video
• DirectShape: Direct Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation
• Deep Convolutional Correlation Iterative Particle Filter for Visual Tracking
• Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers
• Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in Convolutional Networks
• IAN: The Individual Aggregation Network for Person Search
• DocVQA: A Dataset for VQA on Document Images
• Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation
• LLA: Loss-aware Label Assignment for Dense Pedestrian Detection
• Convolutional Character Networks
• Evaluation of Momentum Diverse Input Iterative Fast Gradient Sign Method (M-DI2-FGSM) Based Attack Method on MCS 2018 Adversarial Attacks on Black Box Face Recognition System
• Learning from Multiple Datasets with Heterogeneous and Partial Labels for Universal Lesion Detection in CT
• Automatic Information Extraction from Piping and Instrumentation Diagrams
• Self-Supervised Learning of Depth and Ego-motion with Differentiable Bundle Adjustment
• G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
• Finding the Evidence: Localization-aware Answer Prediction for Text Visual Question Answering
• An Automatic System for Unconstrained Video-Based Face Recognition
• RarePlanes: Synthetic Data Takes Flight
• Object Detection in Video with Spatial-temporal Context Aggregation
• Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation
• S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search
• Adaptive Label Smoothing
• Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation
• Question Type Guided Attention in Visual Question Answering
• ALFA: Agglomerative Late Fusion Algorithm for Object Detection
• Decision-based Universal Adversarial Attack
• CenterMask: single shot instance segmentation with point representation
• 3D for Free: Crossmodal Transfer Learning using HD Maps
• Semi-convolutional Operators for Instance Segmentation
• Learning Cross-modal Context Graph for Visual Grounding
• Gesture Recognition for Initiating Human-to-Robot Handovers
• In the Eye of the Beholder: Gaze and Actions in First Person Video
• Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation
• Local Metrics for Multi-Object Tracking
• Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks
• Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction
• ReFormer: The Relational Transformer for Image Captioning
• Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network
• Improve Object Detection by Data Enhancement based on Generative Adversarial Nets
• Self-Supervised Learning for Semi-Supervised Temporal Action Proposal
• Adversarial Cross-Domain Action Recognition with Co-Attention
• Intention Recognition of Pedestrians and Cyclists by 2D Pose Estimation
• Unsupervised Multiple Person Tracking using AutoEncoder-Based Lifted Multicuts
• Open Domain Generalization with Domain-Augmented Meta-Learning
• Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients
• Multi-Label Generalized Zero Shot Learning for the Classification of Disease in Chest Radiographs
• S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
• TracKlinic: Diagnosis of Challenge Factors in Visual Tracking
• A Multi Camera Unsupervised Domain Adaptation Pipeline for Object Detection in Cultural Sites through Adversarial Learning and Self-Training
• Weakly Supervised Cell Instance Segmentation by Propagating from Detection Response
• Act, Perceive, and Plan in Belief Space for Robot Localization
• ObjectNet Dataset: Reanalysis and Correction
• Contextual Heterogeneous Graph Network for Human-Object Interaction Detection
• Team JL Solution to Google Landmark Recognition 2019
• Category-wise Attack: Transferable Adversarial Examples for Anchor Free Object Detection
• StrObe: Streaming Object Detection from LiDAR Packets
• PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition
• Benchmarking the Robustness of Instance Segmentation Models
• Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression
• VLUC: An Empirical Benchmark for Video-Like Urban Computing on Citywide Crowd and Traffic Prediction
• Iterative Low-Rank Approximation for CNN Compression
• Low-Power Object Counting with Hierarchical Neural Networks
• Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors
• Multi-Task Multi-Sensor Fusion for 3D Object Detection
• DSFD: Dual Shot Face Detector
• Improving Pixel Embedding Learning through Intermediate Distance Regression Supervision for Instance Segmentation
• RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
• HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization
• Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation
• Real-time Mask Detection on Google Edge TPU
• LapNet : Automatic Balanced Loss and Optimal Assignment for Real-Time Dense Object Detection
• Two-Stream AMTnet for Action Detection
• Instance Localization for Self-supervised Detection Pretraining
• Cascaded Human-Object Interaction Recognition
• MM-FSOD: Meta and metric integrated few-shot object detection
• MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
• Rethinking Normalization and Elimination Singularity in Neural Networks
• Bottom-Up Temporal Action Localization with Mutual Regularization
• UAV Visual Teach and Repeat Using Only Semantic Object Features
• Learning Context Graph for Person Search
• Towards a Multi-modal, Multi-task Learning based Pre-training Framework for Document Representation Learning
• CircleNet: Anchor-free Detection with Circle Representation
• Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019
• A Deep Neuro-Fuzzy Network for Image Classification
• TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications
• Semantic keypoint-based pose estimation from single RGB frames
• Fruit Quantity and Quality Estimation using a Robotic Vision System
• CARAFE++: Unified Content-Aware ReAssembly of FEatures
• Image Transformation can make Neural Networks more robust against Adversarial Examples
• Deep Learning Based Computed Tomography Whys and Wherefores
• Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers
• Multi-Sensor 3D Object Box Refinement for Autonomous Driving
• Cross-media Structured Common Space for Multimedia Event Extraction
• Style Normalization and Restitution for Domain Generalization and Adaptation
• What Vision-Language Models `See' when they See Scenes
• Enhancing Object Detection in Adverse Conditions using Thermal Imaging
• Learning latent representations across multiple data domains using Lifelong VAEGAN
• BoundarySqueeze: Image Segmentation as Boundary Squeezing
• Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos
• E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
• Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory
• LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment
• Multilayer Collaborative Low-Rank Coding Network for Robust Deep Subspace Discovery
• PIXOR: Real-time 3D Object Detection from Point Clouds
• A^2-Net: Molecular Structure Estimation from Cryo-EM Density Volumes
• Image Captioning Based on a Hierarchical Attention Mechanism and Policy Gradient Optimization
• ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
• Positional Encoding as Spatial Inductive Bias in GANs
• Single-shot Path Integrated Panoptic Segmentation
• Patch2Pix: Epipolar-Guided Pixel-Level Correspondences
• Malaria Detection and Classificaiton
• Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling
• Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
• Real-world Mapping of Gaze Fixations Using Instance Segmentation for Road Construction Safety Applications
• Rethinking Natural Adversarial Examples for Classification Models
• Multi-person Articulated Tracking with Spatial and Temporal Embeddings
• Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression
• Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization
• Pan-tilt-zoom SLAM for Sports Videos
• Real-Time Text Detection and Recognition
• An Overview Of 3D Object Detection
• TAN: Temporal Affine Network for Real-Time Left Ventricle Anatomical Structure Analysis Based on 2D Ultrasound Videos
• Disjoint Label Space Transfer Learning with Common Factorised Space
• On the Importance of Visual Context for Data Augmentation in Scene Understanding
• Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations
• You Only Look One-level Feature
• hSDB-instrument: Instrument Localization Database for Laparoscopic and Robotic Surgeries
• Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
• Robust Glare Detection: Review, Analysis, and Dataset Release
• LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
• Adversarial Attacks in a Multi-view Setting: An Empirical Study of the Adversarial Patches Inter-view Transferability
• Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
• Detecting Human-Object Interaction via Fabricated Compositional Learning
• OTA: Optimal Transport Assignment for Object Detection
• Spatio-temporal Person Retrieval via Natural Language Queries
• GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
• Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks
• Dynamic Temporal Pyramid Network: A Closer Look at Multi-Scale Modeling for Activity Detection
• Elucidating image-to-set prediction: An analysis of models, losses and datasets
• RevealNet: Seeing Behind Objects in RGB-D Scans
• Localizing Unseen Activities in Video via Image Query
• Deep Rigid Instance Scene Flow
• Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video
• LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding
• Spectro-Temporal RF Identification using Deep Learning
• Persuasive Faces: Generating Faces in Advertisements
• DeSTNet: Densely Fused Spatial Transformer Networks
• Adaptation Across Extreme Variations using Unlabeled Domain Bridges
• Joint Visual Grounding with Language Scene Graphs
• Graph-Structured Referring Expression Reasoning in The Wild
• Multiple Object Tracking with Mixture Density Networks for Trajectory Estimation
• Towards End-to-End Text Spotting in Natural Scenes
• The Problem of Fragmented Occlusion in Object Detection
• A Local-to-Global Approach to Multi-modal Movie Scene Segmentation
• The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
• Towards Compact CNNs via Collaborative Compression
• Unifying Training and Inference for Panoptic Segmentation
• Towards the Internet of Robotic Things: Analysis, Architecture, Components and Challenges
• Using Artificial Intelligence to Analyze Fashion Trends
• The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America
• Rethinking the Route Towards Weakly Supervised Object Localization
• Video-Text Pre-training with Learned Regions
• Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences
• Actions as Moving Points
• Detecting Semantic Parts on Partially Occluded Objects
• Vision-based Robot Manipulation Learning via Human Demonstrations
• Universal Lesion Detection by Learning from Multiple Heterogeneously Labeled Datasets
• APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection
• Acceleration of Actor-Critic Deep Reinforcement Learning for Visual Grasping in Clutter by State Representation Learning Based on Disentanglement of a Raw Input Image
• AutoScale: Learning to Scale for Crowd Counting and Localization
• Image Enhanced Rotation Prediction for Self-Supervised Learning
• Action Recognition for Depth Video using Multi-view Dynamic Images
• Learning Filter Basis for Convolutional Neural Network Compression
• Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
• Anyone here? Smart embedded low-resolution omnidirectional video sensor to measure room occupancy
• Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidents
• Unsupervised Object-Level Representation Learning from Scene Images
• VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations
• Scene Understanding for Autonomous Driving
• Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation
• Bring Your Own Codegen to Deep Learning Compiler
• Feature Pyramid Transformer
• Visual Diagnosis of Dermatological Disorders: Human and Machine Performance
• Unsupervised Deep Representation Learning for Real-Time Tracking
• Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views
• Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networks
• Affordance Transfer Learning for Human-Object Interaction Detection
• Unsupervised Discovery of Object Landmarks as Structural Representations
• Recovering hard-to-find object instances by sampling context-based object proposals
• Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark
• ClickBAIT: Click-based Accelerated Incremental Training of Convolutional Neural Networks
• Gradually Applying Weakly Supervised and Active Learning for Mass Detection in Breast Ultrasound Images
• Robust RGB-based 6-DoF Pose Estimation without Real Pose Annotations
• Towards Practical Implementations of Person Re-Identification from Full Video Frames
• Modeling and Analysis of Energy Harvesting and Smart Grid-Powered Wireless Communication Networks: A Contemporary Survey
• ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
• Weakly Supervised Learning of Multi-Object 3D Scene Decompositions Using Deep Shape Priors
• Regularizing Neural Networks via Adversarial Model Perturbation
• Feature Selective Small Object Detection via Knowledge-based Recurrent Attentive Neural Network
• SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
• CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation
• Meta-learning algorithms for Few-Shot Computer Vision
• From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval
• A Novel Automation-Assisted Cervical Cancer Reading Method Based on Convolutional Neural Network
• A Deep Learning-Based FPGA Function Block Detection Method with Bitstream to Image Transformation
• Regula Sub-rosa: Latent Backdoor Attacks on Deep Neural Networks
• Fast acoustic scattering using convolutional neural networks
• A New Window Loss Function for Bone Fracture Detection and Localization in X-ray Images with Point-based Annotation
• Fast Object Detection in Compressed Video
• Multiple Instance Segmentation in Brachial Plexus Ultrasound Image Using BPMSegNet
• Team Delft's Robot Winner of the Amazon Picking Challenge 2016
• Data-Free Learning of Student Networks
• Reflective Decoding Network for Image Captioning
• Image Classification for Arabic: Assessing the Accuracy of Direct English to Arabic Translations
• Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
• Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension
• Revisiting Knowledge Distillation for Object Detection
• An Effective and Efficient Method for Detecting Hands in Egocentric Videos for Rehabilitation Applications
• Dual Recurrent Attention Units for Visual Question Answering
• Object-Aware Instance Labeling for Weakly Supervised Object Detection
• Deep execution monitor for robot assistive tasks
• 3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection
• Generative Models as a Data Source for Multiview Representation Learning
• Artificial Immune System of Secure Face Recognition Against Adversarial Attacks
• Adaptive Object Detection with Dual Multi-Label Prediction
• Learning to Discretely Compose Reasoning Module Networks for Video Captioning
• Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction
• Self-Supervised Learning by Estimating Twin Class Distributions
• Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer
• No Peeking through My Windows: Conserving Privacy in Personal Drones
• Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion
• ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
• Weakly-Supervised Object Detection Learning through Human-Robot Interaction
• Hire-MLP: Vision MLP via Hierarchical Rearrangement
• End-to-end detection-segmentation network with ROI convolution
• Generating Question Relevant Captions to Aid Visual Question Answering
• Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization
• Image Captioning based on Deep Learning Methods: A Survey
• LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval
• Robust Real-time Pedestrian Detection in Aerial Imagery on Jetson TX2
• Interpreting Adversarial Examples with Attributes
• Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN
• 360-Indoor: Towards Learning Real-World Objects in 360° Indoor Equirectangular Images
• Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
• Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
• Context-Aware Single-Shot Detector
• Simultaneous Region Localization and Hash Coding for Fine-grained Image Retrieval
• FC2RN: A Fully Convolutional Corner Refinement Network for Accurate Multi-Oriented Scene Text Detection
• Synthetic Data Generation and Adaption for Object Detection in Smart Vending Machines
• Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes
• Three Branches: Detecting Actions With Richer Features
• THIA: Accelerating Video Analytics using Early Inference and Fine-Grained Query Planning
• Automatic Detection of Cardiac Chambers Using an Attention-based YOLOv4 Framework from Four-chamber View of Fetal Echocardiography
• The 1st Tiny Object Detection Challenge:Methods and Results
• Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer
• Content-based Analysis of the Cultural Differences between TikTok and Douyin
• Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises
• Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images
• Grounding Object Detections With Transcriptions
• STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training
• Deep Learning in Computer-Aided Diagnosis and Treatment of Tumors: A Survey
• Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View
• POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments
• Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering
• End-to-End Video Object Detection with Spatial-Temporal Transformers
• Road User Detection in Videos
• Simple online and real-time tracking with occlusion handling
• FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
• Object Detection in Videos by High Quality Object Linking
• Robust Object Detection under Occlusion with Context-Aware CompositionalNets
• Exploring the Hierarchy in Relation Labels for Scene Graph Generation
• Amodal Segmentation Based on Visible Region Segmentation and Shape Prior
• Elephants Don't Pack Groceries: Robot Task Planning for Low Entropy Belief States
• NeuNetS: An Automated Synthesis Engine for Neural Network Design
• Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition
• Improving Visual Question Answering by Referring to Generated Paragraph Captions
• Streaming Object Detection for 3-D Point Clouds
• SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
• Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks
• Can Synthetic Data Improve Object Detection Results for Remote Sensing Images?
• Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection
• Learning to Generate Synthetic Data via Compositing
• Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection
• Context and Attribute Grounded Dense Captioning
• Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data
• On the Privacy Risks of Cell-Based NAS Architectures
• SoDA: Multi-Object Tracking with Soft Data Association
• A Context-and-Spatial Aware Network for Multi-Person Pose Estimation
• Localization Distillation for Dense Object Detection
• Deep Structured Feature Networks for Table Detection and Tabular Data Extraction from Scanned Financial Document Images
• A Multi-task Convolutional Neural Network for Autonomous Robotic Grasping in Object Stacking Scenes
• Continual Representation Learning for Biometric Identification
• Atherosclerotic carotid plaques on panoramic imaging: an automatic detection using deep learning with small dataset
• Jo-SRC: A Contrastive Approach for Combating Noisy Labels
• Human Extraction and Scene Transition utilizing Mask R-CNN
• CellLineNet: End-to-End Learning and Transfer Learning For Multiclass Epithelial Breast cell Line Classification via a Convolutional Neural Network
• Spatio-Temporal Action Detection with Multi-Object Interaction
• Learning Student Networks via Feature Embedding
• Small Towers Make Big Differences
• Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking
• CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency
• MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
• Answer Them All! Toward Universal Visual Question Answering Models
• A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis
• Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection
• COVID-19 personal protective equipment detection using real-time deep learning methods
• Optical Music Recognition: State of the Art and Major Challenges
• Epipolar-Guided Deep Object Matching for Scene Change Detection
• Asynchronous Interaction Aggregation for Action Detection
• Towards Precise End-to-end Weakly Supervised Object Detection Network
• Bilinear Graph Networks for Visual Question Answering
• Towards General Purpose Vision Systems
• 2nd Place Solution for Waymo Open Dataset Challenge -- 2D Object Detection
• Context-Aware Crowd Counting
• Unpaired Pose Guided Human Image Generation
• Face Parsing with RoI Tanh-Warping
• Residual Attention based Network for Hand Bone Age Assessment
• SWA Object Detection
• Measuring economic activity from space: a case study using flying airplanes and COVID-19
• Neural Architecture Search by Estimation of Network Structure Distributions
• Object Recognition with and without Objects
• Towards Generalized and Incremental Few-Shot Object Detection
• Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve
• Explainable Goal-Driven Agents and Robots -- A Comprehensive Review
• Learning to Exploit Multiple Vision Modalities by Using Grafted Networks
• Towards High-Quality Temporal Action Detection with Sparse Proposals
• EMPNet: Neural Localisation and Mapping Using Embedded Memory Points
• PAFNet: An Efficient Anchor-Free Object Detector Guidance
• Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps
• Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning
• General Instance Distillation for Object Detection
• RILOD: Near Real-Time Incremental Learning for Object Detection at the Edge
• Adversarially Trained Object Detector for Unsupervised Domain Adaptation
• Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery
• Straight to Shapes: Real-time Detection of Encoded Shapes
• Deep Learning Based Instance Segmentation in 3D Biomedical Images Using Weak Annotation
• TextCohesion: Detecting Text for Arbitrary Shapes
• One-Shot Unsupervised Cross-Domain Detection
• A novel integrated industrial approach with cobots in the age of industry 4.0 through conversational interaction and computer vision
• Generative Zero-shot Network Quantization
• Lidar Panoptic Segmentation in an Open World
• Globally-Aware Multiple Instance Classifier for Breast Cancer Screening
• Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System
• P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds
• A Unified Hardware Architecture for Convolutions and Deconvolutions in CNN
• Semantic Feature Matching for Robust Mapping in Agriculture
• Resilience of Autonomous Vehicle Object Category Detection to Universal Adversarial Perturbations
• Deep Similarity Metric Learning for Real-Time Pedestrian Tracking
• DeRPN: Taking a further step toward more general object detection
• Unsupervised Deep Feature Transfer for Low Resolution Image Classification
• DeepACC:Automate Chromosome Classification based on Metaphase Images using Deep Learning Framework Fused with Prior Knowledge
• Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction
• Monitoring spatial sustainable development: Semi-automated analysis of satellite and aerial images for energy transition and sustainability indicators
• Fire SSD: Wide Fire Modules based Single Shot Detector on Edge Device
• Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension
• Structural Pruning in Deep Neural Networks: A Small-World Approach
• Detecting retail products in situ using CNN without human effort labeling
• iffDetector: Inference-aware Feature Filtering for Object Detection
• Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach
• On the Robustness of Human Pose Estimation
• Diagnosing Error in Temporal Action Detectors
• Artificial Intelligence For Breast Cancer Detection: Trends & Directions
• RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
• GestARLite: An On-Device Pointing Finger Based Gestural Interface for Smartphones and Video See-Through Head-Mounts
• Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos
• ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection
• Image Resizing by Reconstruction from Deep Features
• KIT MOMA: A Mobile Machines Dataset
• Adversarial Parameter Defense by Multi-Step Risk Minimization
• A Large Scale Urban Surveillance Video Dataset for Multiple-Object Tracking and Behavior Analysis
• IAN: Combining Generative Adversarial Networks for Imaginative Face Generation
• Greedy Gradient Ensemble for Robust Visual Question Answering
• V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection
• RigNet: Repetitive Image Guided Network for Depth Completion
• Progressive Cluster Purification for Unsupervised Feature Learning
• A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation
• Channel Locality Block: A Variant of Squeeze-and-Excitation
• Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning
• Domain-Specific Suppression for Adaptive Object Detection
• Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking
• The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale
• Joint Face Detection and Facial Motion Retargeting for Multiple Faces
• Segmentation and Recovery of Superquadric Models using Convolutional Neural Networks
• Journalistic Guidelines Aware News Image Captioning
• All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
• Cascaded Subpatch Networks for Effective CNNs
• I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
• Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection
• Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
• SGNet: A Super-class Guided Network for Image Classification and Object Detection
• Optimizing Through Learned Errors for Accurate Sports Field Registration
• OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
• Democratizing Production-Scale Distributed Deep Learning
• IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking
• IIIT-AR-13K: A New Dataset for Graphical Object Detection in Documents
• Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers
• Modality-Balanced Models for Visual Dialogue
• Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection
• GRIP: Generative Robust Inference and Perception for Semantic Robot Manipulation in Adversarial Environments
• Shift Equivariance in Object Detection
• Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection
• Learning Gating ConvNet for Two-Stream based Methods in Action Recognition
• 1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021
• Weakly supervised cross-domain alignment with optimal transport
• Robustness in Compressed Neural Networks for Object Detection
• Design and Interpretation of Universal Adversarial Patches in Face Detection
• CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network
• Geometry-Aware Video Object Detection for Static Cameras
• A Possible Reason for why Data-Driven Beats Theory-Driven Computer Vision
• Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels
• Probabilistic Embeddings for Cross-Modal Retrieval
• Transferring Domain-Agnostic Knowledge in Video Question Answering
• Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention
• Structure Aware SLAM using Quadrics and Planes
• Beyond Point Clouds: A Knowledge-Aided High Resolution Imaging Radar Deep Detector for Autonomous Driving
• OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection
• Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
• CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images
• Fast Region Proposal Learning for Object Detection for Robotics
• Grab: Fast and Accurate Sensor Processing for Cashier-Free Shopping
• Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images
• Semantic Segmentation from Limited Training Data
• Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions
• Teaching Robots Novel Objects by Pointing at Them
• Guiding the Creation of Deep Learning-based Object Detectors
• DeepApple: Deep Learning-based Apple Detection using a Suppression Mask R-CNN
• Dynamic Edge Weights in Graph Neural Networks for 3D Object Detection
• Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification
• Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection
• Towards Overcoming False Positives in Visual Relationship Detection
• Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection
• Spatial-Temporal Block and LSTM Network for Pedestrian Trajectories Prediction
• Weakly Supervised Object Boundaries
• Semi-Supervised Image Deraining using Gaussian Processes
• Shape-Texture Debiased Neural Network Training
• Deep Regionlets: Blended Representation and Deep Learning for Generic Object Detection
• MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures
• Value of Temporal Dynamics Information in Driving Scene Segmentation
• Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
• Automated Classification of Helium Ingress in Irradiated X-750
• Regularizing Attention Networks for Anomaly Detection in Visual Question Answering
• Constrained R-CNN: A general image manipulation detection model
• Relation Transformer Network
• Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning
• Self-supervised pre-training and contrastive representation learning for multiple-choice video QA
• Attribute-aware Pedestrian Detection in a Crowd
• Seesaw Loss for Long-Tailed Instance Segmentation
• Mixed Supervised Object Detection with Robust Objectness Transfer
• American Sign Language fingerspelling recognition in the wild
• Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition
• HWNet v2: An Efficient Word Image Representation for Handwritten Documents
• Deep Multi-camera People Detection
• A Solution to Product detection in Densely Packed Scenes
• Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving
• Visual Grounding Methods for VQA are Working for the Wrong Reasons!
• Unsupervised Pre-training for Person Re-identification
• DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
• Learning Gaussian Maps for Dense Object Detection
• SiamMOT: Siamese Multi-Object Tracking
• WSSOD: A New Pipeline for Weakly- and Semi-Supervised Object Detection
• Multimodal Learning for Hateful Memes Detection
• PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
• Dont Even Look Once: Synthesizing Features for Zero-Shot Detection
• Detect-and-describe: Joint learning framework for detection and description of objects
• Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting
• Privid: Practical, Privacy-Preserving Video Analytics Queries
• Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN
• Re-ID Driven Localization Refinement for Person Search
• The Importance and the Limitations of Sim2Real for Robotic Manipulation in Precision Agriculture
• Enhancing a Neurocognitive Shared Visuomotor Model for Object Identification, Localization, and Grasping With Learning From Auxiliary Tasks
• QEBA: Query-Efficient Boundary-Based Blackbox Attack
• iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability
• An FPGA-Accelerated Design for Deep Learning Pedestrian Detection in Self-Driving Vehicles
• Exploiting the Inherent Limitation of L0 Adversarial Examples
• The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
• Seeing is Knowing! Fact-based Visual Question Answering using Knowledge Graph Embeddings
• A multi-task convolutional neural network for mega-city analysis using very high resolution satellite imagery and geospatial data
• 3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
• Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification
• Deep ChArUco: Dark ChArUco Marker Pose Estimation
• Self-Supervised Representation Learning for Visual Anomaly Detection
• Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting
• Symmetry and Group in Attribute-Object Compositions
• A Picture May Be Worth a Hundred Words for Visual Question Answering
• Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
• Concatenated Feature Pyramid Network for Instance Segmentation
• Density Map Guided Object Detection in Aerial Images
• Multi-Loss Sub-Ensembles for Accurate Classification with Uncertainty Estimation
• A Structured Model For Action Detection
• Activity Driven Weakly Supervised Object Detection
• Instance-Level Relative Saliency Ranking with Graph Reasoning
• Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
• Incremental Learning for Robot Perception through HRI
• Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
• MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
• MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
• Learning to Fuse Asymmetric Feature Maps in Siamese Trackers
• ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks
• On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving
• Detecting Small, Densely Distributed Objects with Filter-Amplifier Networks and Loss Boosting
• 3D Feature Pyramid Attention Module for Robust Visual Speech Recognition
• Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
• Faceness-Net: Face Detection through Deep Facial Part Responses
• Gaining Extra Supervision via Multi-task learning for Multi-Modal Video Question Answering
• Learning About Objects by Learning to Interact with Them
• 1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020
• Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking
• A Large-Scale Dataset for Benchmarking Elevator Button Segmentation and Character Recognition
• Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation
• Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection
• Learning Effective Visual Relationship Detector on 1 GPU
• The iMaterialist Fashion Attribute Dataset
• Applications of Deep Learning in Fundus Images: A Review
• Active Perception for Ambiguous Objects Classification
• GTNet:Guided Transformer Network for Detecting Human-Object Interactions
• PnP-DETR: Towards Efficient Visual Analysis with Transformers
• Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks
• Semantic Compositional Learning for Low-shot Scene Graph Generation
• ML-EXray: Visibility into ML Deployment on the Edge
• Real-time Embedded Person Detection and Tracking for Shopping Behaviour Analysis
• No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks
• Decoupling Localization and Classification in Single Shot Temporal Action Detection
• Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
• Review: deep learning on 3D point clouds
• Ship Instance Segmentation From Remote Sensing Images Using Sequence Local Context Module
• SaccadeNet: A Fast and Accurate Object Detector
• Dynamically Throttleable Neural Networks (TNN)
• m-RevNet: Deep Reversible Neural Networks with Momentum
• Joint Layout Analysis, Character Detection and Recognition for Historical Document Digitization
• Unsupervised Domain Adaptation for Multispectral Pedestrian Detection
• Moment-Based Domain Adaptation: Learning Bounds and Algorithms
• Learning from Web Data: the Benefit of Unsupervised Object Localization
• Whole-Body Human Pose Estimation in the Wild
• EventNet: Asynchronous Recursive Event Processing
• Unsupervised Temporal Feature Aggregation for Event Detection in Unstructured Sports Videos
• Channel-wise Alignment for Adaptive Object Detection
• Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo
• Cloud-based Image Classification Service Is Not Robust To Simple Transformations: A Forgotten Battlefield
• Rethinking Drone-Based Search and Rescue with Aerial Person Detection
• REGNet: REgion-based Grasp Network for End-to-end Grasp Detection in Point Clouds
• Mixture of Pre-processing Experts Model for Noise Robust Deep Learning on Resource Constrained Platforms
• Pointly-Supervised Instance Segmentation
• BUZz: BUffer Zones for defending adversarial examples in image classification
• VIN: Voxel-based Implicit Network for Joint 3D Object Detection and Segmentation for Lidars
• PerMO: Perceiving More at Once from a Single Image for Autonomous Driving
• Skin disease diagnosis with deep learning: a review
• Learning Image Aesthetic Assessment from Object-level Visual Components
• RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images
• Curriculum By Smoothing
• Hierarchy Parsing for Image Captioning
• VisualMRC: Machine Reading Comprehension on Document Images
• Deep Learning for Automatic Quality Grading of Mangoes: Methods and Insights
• Deeply Aligned Adaptation for Cross-domain Object Detection
• A Parameterized Approach to Personalized Variable Length Summarization of Soccer Matches
• GLSD: The Global Large-Scale Ship Database and Baseline Evaluations
• Segmentation Mask Guided End-to-End Person Search
• 3D Aggregated Faster R-CNN for General Lesion Detection
• Scale Invariant Fully Convolutional Network: Detecting Hands Efficiently
• Learning to Filter: Siamese Relation Network for Robust Tracking
• Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition
• Improving Contrastive Learning by Visualizing Feature Transformation
• FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
• Multi-Class 3D Object Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery
• 3D-DETNet: a Single Stage Video-Based Vehicle Detector
• Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformation
• Modeling Spatio-Temporal Human Track Structure for Action Localization
• Farm land weed detection with region-based deep convolutional neural networks
• Long-distance tiny face detection based on enhanced YOLOv3 for unmanned system
• Fingerspelling recognition in the wild with iterative visual attention
• Let There be Light: Improved Traffic Surveillance via Detail Preserving Night-to-Day Transfer
• Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks
• POI: Multiple Object Tracking with High Performance Detection and Appearance Feature
• DoReMi: First glance at a universal OMR dataset
• SS3D: Single Shot 3D Object Detector
• 3D Pose Estimation for Fine-Grained Object Categories
• Data-Driven Vehicle Trajectory Forecasting
• Visual Attention Model for Cross-sectional Stock Return Prediction and End-to-End Multimodal Market Representation Learning
• SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System
• A Review on Object Pose Recovery: from 3D Bounding Box Detectors to Full 6D Pose Estimators
• Human Following for Wheeled Robot with Monocular Pan-tilt Camera
• Geometry-Aware Instance Segmentation with Disparity Maps
• 3D Crowd Counting via Geometric Attention-guided Multi-View Fusion
• Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
• Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos
• MixModule: Mixed CNN Kernel Module for Medical Image Segmentation
• Multi-scale Aggregation R-CNN for 2D Multi-person Pose Estimation
• Dense Relational Image Captioning via Multi-task Triple-Stream Networks
• Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection
• Mixup Regularization for Region Proposal based Object Detectors
• Context-Aware RCNN: A Baseline for Action Detection in Videos
• Visually Grounded Continual Learning of Compositional Phrases
• Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language
• Straight to Shapes++: Real-time Instance Segmentation Made More Accurate
• Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks
• Efficient Global Multi-object Tracking Under Minimum-cost Circulation Framework
• Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks
• Layerwise Optimization by Gradient Decomposition for Continual Learning
• Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes
• Robust 6D Object Pose Estimation by Learning RGB-D Features
• Label-Attention Transformer with Geometrically Coherent Objects for Image Captioning
• Neural Architecture Refinement: A Practical Way for Avoiding Overfitting in NAS
• Detection as Regression: Certified Object Detection by Median Smoothing
• Stereo Vision Based Single-Shot 6D Object Pose Estimation for Bin-Picking by a Robot Manipulator
• Integrating Image Captioning with Rule-based Entity Masking
• Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection
• Distribution-sensitive Information Retention for Accurate Binary Neural Network
• Point Proposal Network: Accelerating Point Source Detection Through Deep Learning
• Crossover Learning for Fast Online Video Instance Segmentation
• Low-Latency Human Action Recognition with Weighted Multi-Region Convolutional Neural Network
• Multi-label Detection and Classification of Red Blood Cells in Microscopic Images
• StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures
• SAVERS: SAR ATR with Verification Support Based on Convolutional Neural Network
• Learning a Domain Classifier Bank for Unsupervised Adaptive Object Detection
• Towards Generalization and Data Efficient Learning of Deep Robotic Grasping
• Representing Videos as Discriminative Sub-graphs for Action Recognition
• Joint Representation and Truncated Inference Learning for Correlation Filter based Tracking
• Exemplar-Based Open-Set Panoptic Segmentation Network
• Noisy Annotation Refinement for Object Detection
• Rethinking the Artificial Neural Networks: A Mesh of Subnets with a Central Mechanism for Storing and Predicting the Data
• Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation
• IQDet: Instance-wise Quality Distribution Sampling for Object Detection
• AIBench Training: Balanced Industry-Standard AI Training Benchmarking
• Robustness Enhancement of Object Detection in Advanced Driver Assistance Systems (ADAS)
• Edge-Cloud Collaborated Object Detection via Difficult-Case Discriminator
• DeepSEED: 3D Squeeze-and-Excitation Encoder-Decoder Convolutional Neural Networks for Pulmonary Nodule Detection
• SASL: Saliency-Adaptive Sparsity Learning for Neural Network Acceleration
• Mi YouTube es Su YouTube? Analyzing the Cultures using YouTube Thumbnails of Popular Videos
• Social Adaptive Module for Weakly-supervised Group Activity Recognition
• High-order Tensor Pooling with Attention for Action Recognition
• Adaptive Offline Quintuplet Loss for Image-Text Matching
• Learning to Count Objects with Few Exemplar Annotations
• FrostNet: Towards Quantization-Aware Network Architecture Search
• CRACT: Cascaded Regression-Align-Classification for Robust Visual Tracking
• DAWN: Dual Augmented Memory Network for Unsupervised Video Object Tracking
• Two-Stream Region Convolutional 3D Network for Temporal Activity Detection
• A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation
• Tell Me What They're Holding: Weakly-supervised Object Detection with Transferable Knowledge from Human-object Interaction
• AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss
• Class-Aware Robust Adversarial Training for Object Detection
• Membership Inference Attacks Against Object Detection Models
• Jigsaw Clustering for Unsupervised Visual Representation Learning
• Deformable Tube Network for Action Detection in Videos
• Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs
• Soybean pod and seed counting in both outdoor fields and indoor laboratories using unions of deep neural networks
• Investigating Attention Mechanism in 3D Point Cloud Object Detection
• Translate-to-Recognize Networks for RGB-D Scene Recognition
• A Robotic Approach towards Quantifying Epipelagic Bound Plastic Using Deep Visual Models
• Multiple Object Tracking with Motion and Appearance Cues
• Towards Automatic Construction of Diverse, High-quality Image Dataset
• Decoder Choice Network for Meta-Learning
• Overcoming Statistical Shortcuts for Open-ended Visual Counting
• Multi-Layer Content Interaction Through Quaternion Product For Visual Question Answering
• Soft Prototyping Camera Designs for Car Detection Based on a Convolutional Neural Network
• When We First Met: Visual-Inertial Person Localization for Co-Robot Rendezvous
• GTNet: Generative Transfer Network for Zero-Shot Object Detection
• Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
• Self-supervised Robust Object Detectors from Partially Labelled Datasets
• ACP: Automatic Channel Pruning via Clustering and Swarm Intelligence Optimization for CNN
• Learning Channel Inter-dependencies at Multiple Scales on Dense Networks for Face Recognition
• Exploiting Contextual Information with Deep Neural Networks
• Discrete-continuous Action Space Policy Gradient-based Attention for Image-Text Matching
• Motorcycle detection and classification in urban Scenarios using a model based on Faster R-CNN
• CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsense
• Developing a Compressed Object Detection Model based on YOLOv4 for Deployment on Embedded GPU Platform of Autonomous System
• Generic Tubelet Proposals for Action Localization
• Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks
• Chargrid-OCR: End-to-end Trainable Optical Character Recognition for Printed Documents using Instance Segmentation
• Image-based monitoring of bolt loosening through deep-learning-based integrated detection and tracking
• Captioning Images with Novel Objects via Online Vocabulary Expansion
• Joint Multimedia Event Extraction from Video and Article
• Quantum-soft QUBO Suppression for Accurate Object Detection
• Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos
• Efficient Adversarial Attacks for Visual Object Tracking
• A Selective Survey on Versatile Knowledge Distillation Paradigm for Neural Network Models
• Reconstruction of Simulation-Based Physical Field by Reconstruction Neural Network Method
• Data Priming Network for Automatic Check-Out
• ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
• Fusing Saliency Maps with Region Proposals for Unsupervised Object Localization
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion
• iShape: A First Step Towards Irregular Shape Instance Segmentation
• Reviewing continual learning from the perspective of human-level intelligence
• SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation
• User Constrained Thumbnail Generation using Adaptive Convolutions
• Context-Aware Unsupervised Clustering for Person Search
• A Unified Object Motion and Affinity Model for Online Multi-Object Tracking
• Relationship-Embedded Representation Learning for Grounding Referring Expressions
• TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
• FarSee-Net: Real-Time Semantic Segmentation by Efficient Multi-scale Context Aggregation and Feature Space Super-resolution
• AACP: Model Compression by Accurate and Automatic Channel Pruning
• Training Generative Adversarial Networks in One Stage
• Learning to Discriminate Information for Online Action Detection
• CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis
• Towards Panoptic 3D Parsing for Single Image in the Wild
• Accurate Anchor Free Tracking
• A Multi-task Contextual Atrous Residual Network for Brain Tumor Detection & Segmentation
• HALP: Hardware-Aware Latency Pruning
• Skeleton Based Action Recognition using a Stacked Denoising Autoencoder with Constraints of Privileged Information
• Beyond the Camera: Neural Networks in World Coordinates
• Object Detection with a Unified Label Space from Multiple Datasets
• A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks
• Real-Time Visual Object Tracking via Few-Shot Learning
• Towards a Framework for Visual Intelligence in Service Robotics: Epistemic Requirements and Gap Analysis
• E${}^2$BoWs: An End-to-End Bag-of-Words Model via Deep Convolutional Neural Network
• StampNet: unsupervised multi-class object discovery
• Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
• OGNet: Salient Object Detection with Output-guided Attention Module
• Multilevel Language and Vision Integration for Text-to-Clip Retrieval
• Understanding the effects of artifacts on automated polyp detection and incorporating that knowledge via learning without forgetting
• Grasping Detection Network with Uncertainty Estimation for Confidence-Driven Semi-Supervised Domain Adaptation
• ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors
• X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments
• Scaling Object Detection by Transferring Classification Weights
• Context-Aware Zero-Shot Recognition
• Relationship Oriented Affordance Learning through Manipulation Graph Construction
• ROAM: Recurrently Optimizing Tracking Model
• Supervised Visual Attention for Simultaneous Multimodal Machine Translation
• Fast-Tracker 2.0: Improving Autonomy of Aerial Tracking with Active Vision and Human Location Regression
• Dance with Flow: Two-in-One Stream Action Detection
• Learning Sparse Mixture of Experts for Visual Question Answering
• Online Multi-Object Tracking with Dual Matching Attention Networks
• Fast Object Segmentation Learning with Kernel-based Methods for Robotics
• Integrating Objects into Monocular SLAM: Line Based Category Specific Models
• Pavement Distress Detection and Segmentation using YOLOv4 and DeepLabv3 on Pavements in the Philippines
• Visual Tracking via Dynamic Memory Networks
• Adaptive Control of Embedding Strength in Image Watermarking using Neural Networks
• Privacy-preserving Object Detection
• A Deep Multi-task Learning Approach to Skin Lesion Classification
• Towards Adversarially Robust Object Detection
• Real-time Visual Object Tracking with Natural Language Description
• SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation
• Exploring Semantic Relationships for Unpaired Image Captioning
• AIBench Scenario: Scenario-distilling AI Benchmarking
• Perception Improvement for Free: Exploring Imperceptible Black-box Adversarial Attacks on Image Classification
• Adversarial Augmentation for Enhancing Classification of Mammography Images
• Object-aware Feature Aggregation for Video Object Detection
• LAMP: Label Augmented Multimodal Pretraining
• Reverse-engineering Bar Charts Using Neural Networks
• F-Siamese Tracker: A Frustum-based Double Siamese Network for 3D Single Object Tracking
• A Mask R-CNN approach to counting bacterial colony forming units in pharmaceutical development
• Quantifying and Alleviating the Language Prior Problem in Visual Question Answering
• Gated Multi-layer Convolutional Feature Extraction Network for Robust Pedestrian Detection
• COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
• Transferable Active Grasping and Real Embodied Dataset
• CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling
• Rethinking Open-Set Object Detection: Issues, a New Formulation, and Taxonomy
• Progressive Learning of Low-Precision Networks
• SECS: Efficient Deep Stream Processing via Class Skew Dichotomy
• Dynamic Filtering with Large Sampling Field for ConvNets
• Training and Testing Object Detectors with Virtual Images
• AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
• Improving Face Detection Performance with 3D-Rendered Synthetic Data
• Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild
• An End-to-End Foreground-Aware Network for Person Re-Identification
• PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds
• Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds
• SAFCAR: Structured Attention Fusion for Compositional Action Recognition
• Not All Words are Equal: Video-specific Information Loss for Video Captioning
• Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
• Frustum VoxNet for 3D object detection from RGB-D or Depth images
• Multiple Anchor Learning for Visual Object Detection
• Object Detection for Understanding Assembly Instruction Using Context-aware Data Augmentation and Cascade Mask R-CNN
• Multi-Branch Fully Convolutional Network for Face Detection
• Deep learning for brake squeal: vibration detection, characterization and prediction
• Deeply Activated Salient Region for Instance Search
• Parameter Efficient Deep Neural Networks with Bilinear Projections
• A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision
• A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations
• Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
• EnTri: Ensemble Learning with Tri-level Representations for Explainable Scene Recognition
• WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
• Condition directed Multi-domain Adversarial Learning for Loop Closure Detection
• TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network
• Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection
• A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels
• Propose-and-Attend Single Shot Detector
• Domain Adaptive SiamRPN++ for Object Tracking in the Wild
• Scale Optimization for Full-Image-CNN Vehicle Detection
• FRDet: Balanced and Lightweight Object Detector based on Fire-Residual Modules for Embedded Processor of Autonomous Driving
• Learning Orientation-Estimation Convolutional Neural Network for Building Detection in Optical Remote Sensing Image
• OneAdapt: Fast Configuration Adaptation for Video Analytics Applications via Backpropagation
• Autonomous Navigation in Dynamic Environments: Deep Learning-Based Approach
• Visual Semantic Information Pursuit: A Survey
• Robust Data Association for Object-level Semantic SLAM
• Towards Better Object Detection in Scale Variation with Adaptive Feature Selection
• Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck
• Phrase Localization Without Paired Training Examples
• GLiT: Neural Architecture Search for Global and Local Image Transformer
• Obj-GloVe: Scene-Based Contextual Object Embedding
• Efficient Pig Counting in Crowds with Keypoints Tracking and Spatial-aware Temporal Response Filtering
• CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection
• Object Proposal with Kernelized Partial Ranking
• On the Compressive Power of Deep Rectifier Networks for High Resolution Representation of Class Boundaries
• Inner-Scene Similarities as a Contextual Cue for Object Detection
• Attentive CT Lesion Detection Using Deep Pyramid Inference with Multi-Scale Booster
• vireoJD-MM at Activity Detection in Extended Videos
• IMP: Instance Mask Projection for High Accuracy Semantic Segmentation of Things
• Learning Spatio-Temporal Representation with Local and Global Diffusion
• Spatio-temporal Video Re-localization by Warp LSTM
• High Frequency Residual Learning for Multi-Scale Image Classification
• A CNN-RNN Architecture for Multi-Label Weather Recognition
• Collaboration Analysis Using Deep Learning
• A Training-free, One-shot Detection Framework For Geospatial Objects In Remote Sensing Images
• Modularized Textual Grounding for Counterfactual Resilience
• LookUP: Vision-Only Real-Time Precise Underground Localisation for Autonomous Mining Vehicles
• Disentangled Deep Autoencoding Regularization for Robust Image Classification
• Background subtraction on depth videos with convolutional neural networks
• Automatic Surface Area and Volume Prediction on Ellipsoidal Ham using Deep Learning
• Detecting Text in the Wild with Deep Character Embedding Network
• URNet : User-Resizable Residual Networks with Conditional Gating Module
• Speaker Diarization with Region Proposal Network
• A Novel and Efficient Tumor Detection Framework for Pancreatic Cancer via CT Images
• Look, Read and Feel: Benchmarking Ads Understanding with Multimodal Multitask Learning
• Smart Home Appliances: Chat with Your Fridge
• TextTubes for Detecting Curved Text in the Wild
• Knowledge-Enriched Visual Storytelling
• Visual Dialogue State Tracking for Question Generation
• HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs
• Toward Filament Segmentation Using Deep Neural Networks
• CMSN: Continuous Multi-stage Network and Variable Margin Cosine Loss for Temporal Action Proposal Generation
• Grouping Capsules Based Different Types
• Localization-aware Channel Pruning for Object Detection
• Distilling Pixel-Wise Feature Similarities for Semantic Segmentation
• Fine-Grained Object Detection over Scientific Document Images with Region Embeddings
• Team PFDet's Methods for Open Images Challenge 2019
• A Locating Model for Pulmonary Tuberculosis Diagnosis in Radiographs
• Gastroscopic Panoramic View: Application to Automatic Polyps Detection under Gastroscopy
• Practical License Plate Recognition in Unconstrained Surveillance Systems with Adversarial Super-Resolution
• IFR-Net: Iterative Feature Refinement Network for Compressed Sensing MRI
• Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network
• Few-shot Object Detection with Self-adaptive Attention Network for Remote Sensing Images
• Renovating Parsing R-CNN for Accurate Multiple Human Parsing
• Semi-Anchored Detector for One-Stage Object Detection
• Radar+RGB Attentive Fusion for Robust Object Detection in Autonomous Vehicles
• CCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection
• A Smartphone-based System for Real-time Early Childhood Caries Diagnosis
• What leads to generalization of object proposals?
• Weight Equalizing Shift Scaler-Coupled Post-training Quantization
• Deep Learning-based Human Detection for UAVs with Optical and Infrared Cameras: System and Experiments
• Switching Loss for Generalized Nucleus Detection in Histopathology
• Hard Negative Samples Emphasis Tracker without Anchors
• Multi-Level Temporal Pyramid Network for Action Detection
• Self-supervised Object Tracking with Cycle-consistent Siamese Networks
• U2-ONet: A Two-level Nested Octave U-structure with Multiscale Attention Mechanism for Moving Instances Segmentation
• SADet: Learning An Efficient and Accurate Pedestrian Detector
• AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling
• InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling
• Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets
• Understanding Object Detection Through An Adversarial Lens
• Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection
• Domain Contrast for Domain Adaptive Object Detection
• Expandable YOLO: 3D Object Detection from RGB-D Images
• Segmentation task for fashion and apparel
• Improve bone age assessment by learning from anatomical local regions
• Location-Aware Feature Selection Text Detection Network
• DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction
• Large Scale Font Independent Urdu Text Recognition System
• Seismic Shot Gather Noise Localization Using a Multi-Scale Feature-Fusion-Based Neural Network
• GraftNet: An Engineering Implementation of CNN for Fine-grained Multi-label Task
• Detecting and Tracking Communal Bird Roosts in Weather Radar Data
• Farmland Parcel Delineation Using Spatio-temporal Convolutional Networks
• Probabilistic Oriented Object Detection in Automotive Radar
• BiFNet: Bidirectional Fusion Network for Road Segmentation
• Spatial Priming for Detecting Human-Object Interactions
• Semantic Image Manipulation Using Scene Graphs
• Rapid Detection of Aircrafts in Satellite Imagery based on Deep Neural Networks
• A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation
• Disentangled Motif-aware Graph Learning for Phrase Grounding
• Human De-occlusion: Invisible Perception and Recovery for Humans
• Decoupled Spatial Temporal Graphs for Generic Visual Grounding
• PatchNet -- Short-range Template Matching for Efficient Video Processing
• Quality-Aware Network for Human Parsing
• Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning
• Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection
• Differentiable Neural Architecture Learning for Efficient Neural Network Design
• GridTracer: Automatic Mapping of Power Grids using Deep Learning and Overhead Imagery
• Balance-Oriented Focal Loss with Linear Scheduling for Anchor Free Object Detection
• PanoNet3D: Combining Semantic and Geometric Understanding for LiDARPoint Cloud Detection
• A Response Retrieval Approach for Dialogue Using a Multi-Attentive Transformer
• Scene Text Detection with Scribble Lines
• SuperOCR: A Conversion from Optical Character Recognition to Image Captioning
• SRF-GAN: Super-Resolved Feature GAN for Multi-Scale Representation
• Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos
• Amadeus: Scalable, Privacy-Preserving Live Video Analytics
• End-to-end Deep Learning Methods for Automated Damage Detection in Extreme Events at Various Scales
• Compositional Scalable Object SLAM
• Multi-layer Feature Aggregation for Deep Scene Parsing Models
• End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining
• Disaster mapping from satellites: damage detection with crowdsourced point labels
• DPNET: Dual-Path Network for Efficient Object Detectioj with Lightweight Self-Attention
• EMDS-7: Environmental Microorganism Image Dataset Seventh Version for Multiple Object Detection Evaluation
• Understanding Egocentric Hand-Object Interactions from Hand Pose Estimation
• Why Do We Click: Visual Impression-aware News Recommendation
• Scene Graph Generation for Better Image Captioning?
• Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs
• AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance
• RefineCap: Concept-Aware Refinement for Image Captioning
• An Attention Module for Convolutional Neural Networks
• The Multi-Modal Video Reasoning and Analyzing Competition
• FaPN: Feature-aligned Pyramid Network for Dense Image Prediction
• Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchy
• Disentangle Your Dense Object Detector
• Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle
• Neighbor-view Enhanced Model for Vision and Language Navigation
• Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoU
• Cell Detection from Imperfect Annotation by Pseudo Label Selection Using P-classification
• Automatic and explainable grading of meningiomas from histopathology images
• CFTrack: Center-based Radar and Camera Fusion for 3D Multi-Object Tracking
• Positive-unlabeled Learning for Cell Detection in Histopathology Images with Incomplete Annotations
• Universal Adder Neural Networks
• Humble Teachers Teach Better Students for Semi-Supervised Object Detection
• Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding
• Semi-Autoregressive Transformer for Image Captioning
• FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions
• Linguistic Structures as Weak Supervision for Visual Scene Graph Generation
• BCNet: Searching for Network Width with Bilaterally Coupled Network
• FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection
• Drill the Cork of Information Bottleneck by Inputting the Most Important Data
• Decoupled IoU Regression for Object Detection
• A Fast Knowledge Distillation Framework for Visual Recognition
• Consensus Graph Representation Learning for Better Grounded Image Captioning
• Semantic-Aware Environment Perception for Mobile Human-Robot Interaction
• Dense Object Detection Based on De-homogenized Queries
• RGB-D Tracking via Hierarchical Modality Aggregation and Distribution Network
• Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text
• The MIS Check-Dam Dataset for Object Detection and Instance Segmentation Tasks
• Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning
• Detection of E-scooter Riders in Naturalistic Scenes
• Head and Body: Unified Detector and Graph Network for Person Search in Media
• Mask Transfiner for High-Quality Instance Segmentation
• Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine
• FooDI-ML: a large multi-language dataset of food, drinks and groceries images and descriptions
• HR-RCNN: Hierarchical Relational Reasoning for Object Detection
• Progressive Hard-case Mining across Pyramid Levels for Object Detection
• A Better Loss for Visual-Textual Grounding
• Neural Rays for Occlusion-aware Image-based Rendering
• Modeling Explicit Concerning States for Reinforcement Learning in Visual Dialogue
• End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization
• TabLeX: A Benchmark Dataset for Structure and Content Information Extraction from Scientific Tables
• CASIA-Face-Africa: A Large-scale African Face Image Database
• Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
• RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users
• MODS -- A USV-oriented object detection and obstacle segmentation benchmark
• Cross-Modal Generative Augmentation for Visual Question Answering
• EagerMOT: 3D Multi-Object Tracking via Sensor Fusion
• Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous Vehicles
• Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
• EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case
• Simple multi-dataset detection
• MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
• MLPerf Mobile Inference Benchmark
• A Unified Mixture-View Framework for Unsupervised Representation Learning
• Interpretable Visual Reasoning via Induced Symbolic Space
• From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video
• Object Tracking Using Spatio-Temporal Future Prediction
• Learning Spatio-Appearance Memory Network for High-Performance Visual Tracking
• Multi-Label Activity Recognition using Activity-specific Features and Activity Correlations
• Learning Person Re-identification Models from Videos with Weak Supervision
• A Deep Ordinal Distortion Estimation Approach for Distortion Rectification
• AQD: Towards Accurate Fully-Quantized Object Detection
• COBE: Contextualized Object Embeddings from Narrated Instructional Video
• Representation Sharing for Fast Object Detector Search and Beyond
• Deep Learning Methods for Real-time Detection and Analysis of Wagner Ulcer Classification System
• Can 3D Adversarial Logos Cloak Humans?
• Region Proposal Network with Graph Prior and IoU-Balance Loss for Landmark Detection in 3D Ultrasound
• Multi-Plateau Ensemble for Endoscopic Artefact Segmentation and Detection
• On the effectiveness of convolutional autoencoders on image-based personalized recommender systems
• ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
• Face Anti-Spoofing by Learning Polarization Cues in a Real-World Scenario
• The State of Lifelong Learning in Service Robots: Current Bottlenecks in Object Perception and Manipulation
• End-to-end Autonomous Driving Perception with Sequential Latent Representation Learning
• Coupled Network for Robust Pedestrian Detection with Gated Multi-Layer Feature Extraction and Deformable Occlusion Handling
• Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images
• Oriented Objects as pairs of Middle Lines
• Defective Convolutional Networks
• Large Scale Open-Set Deep Logo Detection
• Deep Mixture Density Network for Probabilistic Object Detection
• To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis?
• Searching for Accurate Binary Neural Architectures
• Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum
• Linear Context Transform Block
• Temporal Reasoning Graph for Activity Recognition
• An Objectness Score for Accurate and Fast Detection during Navigation
• High Performance Visual Object Tracking with Unified Convolutional Networks
• Image Captioning with Unseen Objects
• Efficient Method for Categorize Animals in the Wild
• Reprojection R-CNN: A Fast and Accurate Object Detector for 360° Images
• Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction
• Efficient Object Embedding for Spliced Image Retrieval
• Training Quantized Neural Networks with a Full-precision Auxiliary Module
• Geometry-constrained Car Recognition Using a 3D Perspective Network
• MUSCO: Multi-Stage Compression of neural networks
• FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds
• A Single-shot Object Detector with Feature Aggragation and Enhancement
• Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images
• DOSED: a deep learning approach to detect multiple sleep micro-events in EEG signal
• A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization
• Spatially-weighted Anomaly Detection
• Towards a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection
• Object Detection from Scratch with Deep Supervision
• Weakly- and Semi-Supervised Panoptic Segmentation
• LiDAR and Camera Detection Fusion in a Real Time Industrial Multi-Sensor Collision Avoidance System
• Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
• Face-Cap: Image Captioning using Facial Expression Analysis
• Deep Global-Connected Net With The Generalized Multi-Piecewise ReLU Activation in Deep Learning
• Object Localization with a Weakly Supervised CapsNet
• Survey of Face Detection on Low-quality Images
• End-to-End Saliency Mapping via Probability Distribution Prediction
• Deep cross-domain building extraction for selective depth estimation from oblique aerial imagery
• Learnable Histogram: Statistical Context Features for Deep Neural Networks
• The Automatic Identification of Butterfly Species
• Visual Manipulation Relationship Network
• Temporally Identity-Aware SSD with Attentional LSTM
• DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion
• Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation
• Face Detection with End-to-End Integration of a ConvNet and a 3D Model
• Real-Time Grasping Strategies Using Event Camera
• FAN: Focused Attention Networks
• Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
• Multi-Kernel Diffusion CNNs for Graph-Based Learning on Point Clouds
• Autonomous detection of molecular configurations in microscopic images based on deep convolutional neural network
• Efficient Model Performance Estimation via Feature Histories
• Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera
• Learning to Navigate for Fine-grained Classification
• Are object detection assessment criteria ready for maritime computer vision?
• Separating Skills and Concepts for Novel Visual Question Answering
• Semi-supervised Cell Detection in Time-lapse Images Using Temporal Consistency
• Advanced Multiple Linear Regression Based Dark Channel Prior Applied on Dehazing Image and Generating Synthetic Haze
• Boosting ship detection in SAR images with complementary pretraining techniques
• Structure Information is the Key: Self-Attention RoI Feature Extractor in 3D Object Detection
• Achieving Human Parity on Visual Question Answering
• Region-Manipulated Fusion Networks for Pancreatitis Recognition
• Sequential End-to-end Network for Efficient Person Search
• UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning
• An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information
• Deep Lidar CNN to Understand the Dynamics of Moving Vehicles
• Single Shot Scene Text Retrieval
• What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions
• Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos
• Stereo Object Matching Network
• Learning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images
• Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery
• THAT: Two Head Adversarial Training for Improving Robustness at Scale
• From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection
• Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection
• REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter
• Deformation Robust Roto-Scale-Translation Equivariant CNNs
• Fully Convolutional Scene Graph Generation
• Improving Network Slimming with Nonconvex Regularization
• Semi-Online Knowledge Distillation
• Federated Few-Shot Learning with Adversarial Learning
• Perceptual Attention-based Predictive Control
• DIODE: Dilatable Incremental Object Detection
• Towards Object Detection from Motion
• TL-SDD: A Transfer Learning-Based Method for Surface Defect Detection with Few Samples
• Dense Scene Multiple Object Tracking with Box-Plane Matching
• CAROM -- Vehicle Localization and Traffic Scene Reconstruction from Monocular Cameras on Road Infrastructures
• Localizing Visual Sounds the Hard Way
• Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes
• Learning Context-Aware Embedding for Person Search
• ZS-SLR: Zero-Shot Sign Language Recognition from RGB-D Videos
• Temporal Knowledge Consistency for Unsupervised Visual Representation Learning
• Learning Visual Affordances with Target-Orientated Deep Q-Network to Grasp Objects by Harnessing Environmental Fixtures
• Fashion-Guided Adversarial Attack on Person Segmentation
• Characters Detection on Namecard with faster RCNN
• MetricOpt: Learning to Optimize Black-Box Evaluation Metrics
• Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors
• Decoupled Dynamic Filter Networks
• Updatable Siamese Tracker with Two-stage One-shot Learning
• Where are the Blobs: Counting by Localization with Point Supervision
• Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning
• Decoupled Gradient Harmonized Detector for Partial Annotation: Application to Signet Ring Cell Detection
• Unsupervised Industrial Anomaly Detection via Pattern Generative and Contrastive Networks
• Goal-driven text descriptions for images
• Extract and Merge: Merging extracted humans from different images utilizing Mask R-CNN
• Image-based Detection of Surface Defects in Concrete during Construction
• Query-based Hard-Image Retrieval for Object Detection at Test Time
• Fast Template Matching and Update for Video Object Tracking and Segmentation
• Learning Question-Guided Video Representation for Multi-Turn Video Question Answering
• Lightweight Mask R-CNN for Long-Range Wireless Power Transfer Systems
• Deep Learning-based mitosis detection in breast cancer histologic samples
• RFBTD: RFB Text Detector
• Deep neural networks can be improved using human-derived contextual expectations
• Document Layout Annotation: Database and Benchmark in the Domain of Public Affairs
• ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences
• Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation
• Facial Action Unit Detection on ICU Data for Pain Assessment
• Mask R-CNN Based Object Detection for Intelligent Wireless Power Transfer
• Measuring and Predicting Tag Importance for Image Retrieval
• Multi-Scale Time-Frequency Attention for Acoustic Event Detection
• Hybrid Attention for Automatic Segmentation of Whole Fetal Head in Prenatal Ultrasound Volumes
• Weakly Supervised Dataset Collection for Robust Person Detection
• Towards Embodied Scene Description
• Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases
• TSDM: Tracking by SiamRPN++ with a Depth-refiner and a Mask-generator
• A Multimodal Sentiment Dataset for Video Recommendation
• Scope Head for Accurate Localization in Object Detection
• EDDA: Explanation-driven Data Augmentation to Improve Explanation Faithfulness
• Video-based Person Re-identification without Bells and Whistles
• WixUp: A General Data Augmentation Framework for Wireless Perception in Tracking of Humans
• K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
• Unsupervised data augmentation for object detection
• More Than Just Attention: Improving Cross-Modal Attentions with Contrastive Constraints for Image-Text Matching
• Tensor Composition Net for Visual Relationship Prediction
• You Cannot Easily Catch Me: A Low-Detectable Adversarial Patch for Object Detectors
• Social Behavioral Phenotyping of Drosophila with a2D-3D Hybrid CNN Framework
• mr2NST: Multi-Resolution and Multi-Reference Neural Style Transfer for Mammography
• Weakly Supervised Action Selection Learning in Video
• Detecting Curve Text with Local Segmentation Network and Curve Connection
• MSDU-net: A Multi-Scale Dilated U-net for Blur Detection
• Learning Instance-wise Sparsity for Accelerating Deep Models
• Towards Robust Pattern Recognition: A Review
• Semantic Dense Reconstruction with Consistent Scene Segments
• Exploiting Visual Semantic Reasoning for Video-Text Retrieval
• GPR: Grasp Pose Refinement Network for Cluttered Scenes
• AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
• Proposal Flow: Semantic Correspondences from Object Proposals
• Transformer Assisted Convolutional Network for Cell Instance Segmentation
• Materials In Paintings (MIP): An interdisciplinary dataset for perception, art history, and computer vision
• Combating Ambiguity for Hash-code Learning in Medical Instance Retrieval
• Optical deep learning nano-profilometry
• Horizontal-to-Vertical Video Conversion
• Deep Learning Acceleration Techniques for Real Time Mobile Vision Applications
• Image Captioning with Compositional Neural Module Networks
• Saliency deep embedding for aurora image search
• AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points
• Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detection
• Robust and Efficient Graph Correspondence Transfer for Person Re-identification
• Are you doing what I say? On modalities alignment in ALFRED
• Slot Based Image Augmentation System for Object Detection
• Understanding of Emotion Perception from Art
• Semi-Autoregressive Image Captioning
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• 2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge
• Deep Learning Estimation of Absorbed Dose for Nuclear Medicine Diagnostics
• ALET (Automated Labeling of Equipment and Tools): A Dataset, a Baseline and a Usecase for Tool Detection in the Wild
• LGA-RCNN: Loss-Guided Attention for Object Detection
• DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
• MT: Multi-Perspective Feature Learning Network for Scene Text Detection
• LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
• Adma: A Flexible Loss Function for Neural Networks
• Understanding Video Content: Efficient Hero Detection and Recognition for the Game "Honor of Kings"
• Improving Object Detection with Selective Self-supervised Self-training
• Learning Instance-Aware Object Detection Using Determinantal Point Processes
• Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation
• Locality-Aware Rotated Ship Detection in High-Resolution Remote Sensing Imagery Based on Multi-Scale Convolutional Network
• Osteoporosis Prescreening using Panoramic Radiographs through a Deep Convolutional Neural Network with Attention Mechanism
• Person Identification with Visual Summary for a Safe Access to a Smart Home
• Prime-Aware Adaptive Distillation
• Learning with Rethinking: Recurrently Improving Convolutional Neural Networks through Feedback
• Human Motion Capture Using a Drone
• Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation
• Camera On-boarding for Person Re-identification using Hypothesis Transfer Learning
• FPAN: Fine-grained and Progressive Attention Localization Network for Data Retrieval
• Enabling Incremental Knowledge Transfer for Object Detection at the Edge
• Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts
• Search Spaces for Neural Model Training
• A Joint Intensity-Neuromorphic Event Imaging System for Resource Constrained Devices
• Relevance Attack on Detectors
• Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning
• Learning Relation Alignment for Calibrated Cross-modal Retrieval
• Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving
• Feedback Attention for Cell Image Segmentation
• Certainty Driven Consistency Loss on Multi-Teacher Networks for Semi-Supervised Learning
• MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation
• Dynamic Resolution Network
• On Applying Machine Learning/Object Detection Models for Analysing Digitally Captured Physical Prototypes from Engineering Design Projects
• Object-Aware Multi-Branch Relation Networks for Spatio-Temporal Video Grounding
• SeqDialN: Sequential Visual Dialog Networks in Joint Visual-Linguistic Representation Space
• QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM
• Strawberry Detection using Mixed Training on Simulated and Real Data
• DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
• Temporal Action Localization with Variance-Aware Networks
• Few-Shot Object Detection via Knowledge Transfer
• Open-World Entity Segmentation
• Deep Volumetric Universal Lesion Detection using Light-Weight Pseudo 3D Convolution and Surface Point Regression
• Image Captioning with Integrated Bottom-Up and Multi-level Residual Top-Down Attention for Game Scene Understanding
• Task-driven Semantic Coding via Reinforcement Learning
• LabelEnc: A New Intermediate Supervision Method for Object Detection
• supervised adptive threshold network for instance segmentation
• Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization
• Financial ticket intelligent recognition system based on deep learning
• Robust Regression via Deep Negative Correlation Learning
• 3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations
• Few-shot Learning with Global Relatedness Decoupled-Distillation
• Greedy Network Enlarging
• Visible Feature Guidance for Crowd Pedestrian Detection
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection
• Curriculum Learning with Diversity for Supervised Computer Vision Tasks
• Multiple interaction learning with question-type prior knowledge for constraining answer search space in visual question answering
• Unsupervised Object Detection with LiDAR Clues
• Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
• Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
• An Empirical Study of DNNs Robustification Inefficacy in Protecting Visual Recommenders
• FDNAS: Improving Data Privacy and Model Diversity in AutoML
• ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras
• STELA: A Real-Time Scene Text Detector with Learned Anchor
• An Action Recognition network for specific target based on rMC and RPN
• Rethinking Task and Metrics of Instance Segmentation on 3D Point Clouds
• ASSD: Attentive Single Shot Multibox Detector
• Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency
• Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations
• LIP: Learning Instance Propagation for Video Object Segmentation
• A Self Validation Network for Object-Level Human Attention Estimation
• Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors
• Single View Physical Distance Estimation using Human Pose
• Enforcing Reasoning in Visual Commonsense Reasoning
• An Autonomous Approach to Measure Social Distances and Hygienic Practices during COVID-19 Pandemic in Public Open Spaces
• Learning Temporal Action Proposals With Fewer Labels
• NADS-Net: A Nimble Architecture for Driver and Seat Belt Detection via Convolutional Neural Networks
• ActBERT: Learning Global-Local Video-Text Representations
• Bi-Dimensional Feature Alignment for Cross-Domain Object Detection
• Group-based Distinctive Image Captioning with Memory Attention
• Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization
• Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection
• Event Recognition with Automatic Album Detection based on Sequential Processing, Neural Attention and Image Captioning
• Temporal Action Localization using Long Short-Term Dependency
• The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation
• Towards Real-Time Advancement of Underwater Visual Quality with GAN
• Congestion Analysis of Convolutional Neural Network-Based Pedestrian Counting Methods on Helicopter Footage
• Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design
• Is First Person Vision Challenging for Object Tracking?
• Energy Drain of the Object Detection Processing Pipeline for Mobile Devices: Analysis and Implications
• Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB
• Location-aware Upsampling for Semantic Segmentation
• Ellipse Detection and Localization with Applications to Knots in Sawn Lumber Images
• A gamified simulator and physical platform for self-driving algorithm training and validation
• Descriptor-Free Multi-View Region Matching for Instance-Wise 3D Reconstruction
• Batch Normalization with Enhanced Linear Transformation
• Learning a metacognition for object perception
• SISA: Securing Images by Selective Alteration
• Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection
• Context-Gated Convolution
• Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks
• Global Context Aware RCNN for Object Detection
• DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog
• Maria: A Visual Experience Powered Conversational Agent
• Visual Agreement Regularized Training for Multi-Modal Machine Translation
• DeepACEv2: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks
• Aggressive Perception-Aware Navigation using Deep Optical Flow Dynamics and PixelMPC
• ParaNet: Deep Regular Representation for 3D Point Clouds
• Frequency Disentangled Residual Network
• Deep Residual Dense U-Net for Resolution Enhancement in Accelerated MRI Acquisition
• Efficient Human Pose Estimation with Depthwise Separable Convolution and Person Centroid Guided Joint Grouping
• Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection
• MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion
• Deep Learning based Multi-Modal Sensing for Tracking and State Extraction of Small Quadcopters
• ShuffleDet: Real-Time Vehicle Detection Network in On-board Embedded UAV Imagery
• One-Shot Domain Adaptation For Face Generation
• Object Instance Mining for Weakly Supervised Object Detection
• Robust Segmentation of Optic Disc and Cup from Fundus Images Using Deep Neural Networks
• Inverting and Understanding Object Detectors
• Widening and Squeezing: Towards Accurate and Efficient QNNs
• Answer-checking in Context: A Multi-modal FullyAttention Network for Visual Question Answering
• A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection
• Real-time Human-Robot Collaborative Manipulations of Cylindrical and Cubic Objects via Geometric Primitives and Depth Information
• AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite
• EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement
• Object 6D Pose Estimation with Non-local Attention
• Feature-Driven Super-Resolution for Object Detection
• Global Context Networks
• Expressing Objects just like Words: Recurrent Visual Embedding for Image-Text Matching
• Towards Understanding the Effectiveness of Attention Mechanism
• Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos
• An Artificial Intelligence System for Combined Fruit Detection and Georeferencing, Using RTK-Based Perspective Projection in Drone Imagery
• Morphological Networks for Image De-raining
• PVSS: A Progressive Vehicle Search System for Video Surveillance Networks
• Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction
• SOLO: A Simple Framework for Instance Segmentation
• PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation
• Towards Fully Automated Manga Translation
• Colorectal Polyp Detection in Real-world Scenario: Design and Experiment Study
• Towards Pedestrian Detection Using RetinaNet in ECCV 2018 Wider Pedestrian Detection Challenge
• WDR FACE: The First Database for Studying Face Detection in Wide Dynamic Range
• Simultaneous x, y Pixel Estimation and Feature Extraction for Multiple Small Objects in a Scene: A Description of the ALIEN Network
• Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection
• Min-Entropy Latent Model for Weakly Supervised Object Detection
• Mixup Without Hesitation
• LiDAR-assisted Large-scale Privacy Protection in Street-view Cycloramas
• You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding
• Towards Cross-Modal Forgery Detection and Localization on Live Surveillance Videos
• LIT: Light-field Inference of Transparency for Refractive Object Localization
• SurveilEdge: Real-time Video Query based on Collaborative Cloud-Edge Deep Learning
• Towards Deep Learning Assisted Autonomous UAVs for Manipulation Tasks in GPS-Denied Environments
• Deep Reinforcement Learning for Active Human Pose Estimation
• Natural Language Video Localization with Learnable Moment Proposals
• Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths
• Real Time Incremental Foveal Texture Mapping for Autonomous Vehicles
• An Improvement of Object Detection Performance using Multi-step Machine Learnings
• Biologically Inspired Visual System Architecture for Object Recognition in Autonomous Systems
• Weak Novel Categories without Tears: A Survey on Weak-Shot Learning
• Mask-GD Segmentation Based Robotic Grasp Detection
• Scene-Aware Error Modeling of LiDAR/Visual Odometry for Fusion-based Vehicle Localization
• Global Convergence and Geometric Characterization of Slow to Fast Weight Evolution in Neural Network Training for Classifying Linearly Non-Separable Data
• L-Verse: Bidirectional Generation Between Image and Text
• Progressive Cross-Stream Cooperation in Spatial and Temporal Domain for Action Localization
• R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving
• LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units
• Semantic Segmentation for Compound figures
• Visual Question Answering based on Local-Scene-Aware Referring Expression Generation
• Recognizing Object Affordances to Support Scene Reasoning for Manipulation Tasks
• Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images
• Vehicle Detection in Deep Learning
• MLMA-Net: multi-level multi-attentional learning for multi-label object detection in textile defect images
• MLOD: A multi-view 3D object detection based on robust feature fusion method
• PointINS: Point-based Instance Segmentation
• An End-to-End Food Image Analysis System
• Domain Adaptation Regularization for Spectral Pruning
• Histogram of Cell Types: Deep Learning for Automated Bone Marrow Cytology
• Denoising Large-Scale Image Captioning from Alt-text Data using Content Selection Models
• BiDet: An Efficient Binarized Object Detector
• Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration
• PBRnet: Pyramidal Bounding Box Refinement to Improve Object Localization Accuracy
• IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks
• Bringing in the outliers: A sparse subspace clustering approach to learn a dictionary of mouse ultrasonic vocalizations
• Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning
• DEPARA: Deep Attribution Graph for Deep Knowledge Transferability
• Natural Adversarial Objects
• Neural Twins Talk
• Multi-Person Pose Estimation with Enhanced Feature Aggregation and Selection
• Quantifying the presence of graffiti in urban environments
• A New Few-shot Segmentation Network Based on Class Representation
• BABO: Background Activation Black-Out for Efficient Object Detection
• Pseudo-Labeling for Small Lesion Detection on Diabetic Retinopathy Images
• Neural Mesh Refiner for 6-DoF Pose Estimation
• Live Reconstruction of Large-Scale Dynamic Outdoor Worlds
• Single Shot Video Object Detector
• Impression Space from Deep Template Network
• Tackling the Problem of Limited Data and Annotations in Semantic Segmentation
• Learning to Parse Wireframes in Images of Man-Made Environments
• ContourRend: A Segmentation Method for Improving Contours by Rendering
• Tracking the Untrackable
• Graph-Based Social Relation Reasoning
• Volumetric Transformer Networks
• SparseTrain: Exploiting Dataflow Sparsity for Efficient Convolutional Neural Networks Training
• Visual Relation Grounding in Videos
• Computer-aided Tumor Diagnosis in Automated Breast Ultrasound using 3D Detection Network
• LiDAR point-cloud processing based on projection methods: a comparison
• Implicit Saliency in Deep Neural Networks
• Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions
• Leveraging Localization for Multi-camera Association
• Low-Light Maritime Image Enhancement with Regularized Illumination Optimization and Deep Noise Suppression
• Woodpecker-DL: Accelerating Deep Neural Networks via Hardware-Aware Multifaceted Optimizations
• Sparse Coding Driven Deep Decision Tree Ensembles for Nuclear Segmentation in Digital Pathology Images
• Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention
• AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency
• Layout-induced Video Representation for Recognizing Agent-in-Place Actions
• Object Detection in the Context of Mobile Augmented Reality
• CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization
• Vision-based deep execution monitoring
• Bosch Deep Learning Hardware Benchmark
• Graphical Object Detection in Document Images
• Fast Single-shot Ship Instance Segmentation Based on Polar Template Mask in Remote Sensing Images
• Learning Fixation Point Strategy for Object Detection and Classification
• Online Spatiotemporal Action Detection and Prediction via Causal Representations
• Modification method for single-stage object detectors that allows to exploit the temporal behaviour of a scene to improve detection accuracy
• Few-shot Object Detection with Feature Attention Highlight Module in Remote Sensing Images
• Geometric Neural Phrase Pooling: Modeling the Spatial Co-occurrence of Neurons
• Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
• An unsupervised deep learning framework via integrated optimization of representation learning and GMM-based modeling
• Learning Joint Representations of Videos and Sentences with Web Image Search
• Learning semantic Image attributes using Image recognition and knowledge graph embeddings
• Deep Collective Learning: Learning Optimal Inputs and Weights Jointly in Deep Neural Networks
• CoFF: Cooperative Spatial Feature Fusion for 3D Object Detection on Autonomous Vehicles
• Self-grouping Convolutional Neural Networks
• Smart-Inspect: Micro Scale Localization and Classification of Smartphone Glass Defects for Industrial Automation
• Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score
• Deep Local Global Refinement Network for Stent Analysis in IVOCT Images
• Feature Fusion Detector for Semantic Cognition of Remote Sensing
• Hidden State Guidance: Improving Image Captioning using An Image Conditioned Autoencoder
• Regularizing Neural Networks via Stochastic Branch Layers
• Semi-Automatic Crowdsourcing Tool for Online Food Image Collection and Annotation
• Organ At Risk Segmentation with Multiple Modality
• Assisting human experts in the interpretation of their visual process: A case study on assessing copper surface adhesive potency
• Literature Review: Human Segmentation with Static Camera
• ROI Pooled Correlation Filters for Visual Tracking
• Investigations of the Influences of a CNN's Receptive Field on Segmentation of Subnuclei of Bilateral Amygdalae
• A Computing Kernel for Network Binarization on PyTorch
• Mini Lesions Detection on Diabetic Retinopathy Images via Large Scale CNN Features
• Computer-Aided Clinical Skin Disease Diagnosis Using CNN and Object Detection Models
• Adaptive Multi-scale Detection of Acoustic Events
• Occluded Pedestrian Detection with Visible IoU and Box Sign Predictor
• OptiBox: Breaking the Limits of Proposals for Visual Grounding
• Better Understanding Hierarchical Visual Relationship for Image Caption
• Water Supply Prediction Based on Initialized Attention Residual Network
• Autonomous Removal of Perspective Distortion for Robotic Elevator Button Recognition
• A Multi-oriented Chinese Keyword Spotter Guided by Text Line Detection
• A Holistic Approach for Data-Driven Object Cutout
• Multi-Scale Weight Sharing Network for Image Recognition
• Contextual Sense Making by Fusing Scene Classification, Detections, and Events in Full Motion Video
• IG-TRACK: IOU Guided Siamese Networks for visual object tracking
• SafeNet: An Assistive Solution to Assess Incoming Threats for Premises
• Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation
• Measuring the Utilization of Public Open Spaces by Deep Learning: a Benchmark Study at the Detroit Riverfront
• Joint Deep Learning of Facial Expression Synthesis and Recognition
• Learning Hyperspectral Feature Extraction and Classification with ResNeXt Network
• Rotational Rectification Network: Enabling Pedestrian Detection for Mobile Vision
• Layered Embeddings for Amodal Instance Segmentation
• An End-to-End Framework for Unsupervised Pose Estimation of Occluded Pedestrians
• Deep CTR Prediction in Display Advertising
• Learning Object Scale With Click Supervision for Object Detection
• Joint 2D-3D Breast Cancer Classification
• A Video Analysis Method on Wanfang Dataset via Deep Neural Network
• Weeping and Gnashing of Teeth: Teaching Deep Learning in Image and Video Processing Classes
• Residual-CNDS for Grand Challenge Scene Dataset
• Effect of Various Regularizers on Model Complexities of Neural Networks in Presence of Input Noise
• Vision Based Picking System for Automatic Express Package Dispatching
• Dataset Culling: Towards Efficient Training Of Distillation-Based Domain Specific Models
• Detecting Gaze Towards Eyes in Natural Social Interactions and its Use in Child Assessment
• Segmentation of Objects by Hashing
• Spiking Neural Network based Region Proposal Networks for Neuromorphic Vision Sensors
• IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules
• Weakly Supervised Instance Segmentation by Deep Community Learning
• On Class Imbalance and Background Filtering in Visual Relationship Detection
• CycleCluster: Modernising Clustering Regularisation for Deep Semi-Supervised Classification
• Gun Source and Muzzle Head Detection
• Weighted Average Precision: Adversarial Example Detection in the Visual Perception of Autonomous Vehicles
• 3D Object Detection on Point Clouds using Local Ground-aware and Adaptive Representation of scenes' surface
• Competing Ratio Loss for Discriminative Multi-class Image Classification
• Network Pruning via Annealing and Direct Sparsity Control
• Localizing Interpretable Multi-scale informative Patches Derived from Media Classification Task
• Two-stage multi-scale breast mass segmentation for full mammogram analysis without user intervention
• On evaluating CNN representations for low resource medical image classification
• A High-Performance Object Proposals based on Horizontal High Frequency Signal
• OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement
• Learning Object Permanence from Video
• TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge
• Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition
• Using constraint structure and an improved object detection network to detect the 12^{th} Vertebra from CT images with a limited field of view for image-guided radiotherapy
• iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
• Convolutional Neural Networks for User Identificationbased on Motion Sensors Represented as Image
• Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network
• Interaction Graphs for Object Importance Estimation in On-road Driving Videos
• ZSTAD: Zero-Shot Temporal Activity Detection
• Affinity Graph Supervision for Visual Recognition
• Towards Detection of Sheep Onboard a UAV
• DMV: Visual Object Tracking via Part-level Dense Memory and Voting-based Retrieval
• Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection
• On the Evaluation of Prohibited Item Classification and Detection in Volumetric 3D Computed Tomography Baggage Security Screening Imagery
• Scalable Change Retrieval Using Deep 3D Neural Codes
• Conditionally Learn to Pay Attention for Sequential Visual Task
• Long Short-Term Relation Networks for Video Action Detection
• EOLO: Embedded Object Segmentation only Look Once
• Machine Vision for Improved Human-Robot Cooperation in Adverse Underwater Conditions
• Spatio-temporal Tubelet Feature Aggregation and Object Linking in Videos
• Visual Question Answering Using Semantic Information from Image Descriptions
• Deep Learning Meets SAR
• Learning to Reweight with Deep Interactions
• A method for detecting text of arbitrary shapes in natural scenes that improves text spotting
• Learning Camera-Aware Noise Models
• Enhancing and Learning Denoiser without Clean Reference
• Group Whitening: Balancing Learning Efficiency and Representational Capacity
• Feature Flow: In-network Feature Flow Estimation for Video Object Detection
• Graph-based Heuristic Search for Module Selection Procedure in Neural Module Network
• Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs
• Can images help recognize entities? A study of the role of images for Multimodal NER
• Artificial Intelligence: Research Impact on Key Industries; the Upper-Rhine Artificial Intelligence Symposium (UR-AI 2020)
• Neighbourhood Distillation: On the benefits of non end-to-end distillation
• Large Product Key Memory for Pretrained Language Models
• Contralaterally Enhanced Networks for Thoracic Disease Detection
• Interpretable Neural Computation for Real-World Compositional Visual Question Answering
• WeightAlign: Normalizing Activations by Weight Alignment
• Adaptive and Azimuth-Aware Fusion Network of Multimodal Local Features for 3D Object Detection
• Learning to Reconstruct and Segment 3D Objects
• Image Captioning with Visual Object Representations Grounded in the Textual Modality
• Universal Bounding Box Regression and Its Applications
• Learning Quantized Neural Nets by Coarse Gradient Method for Non-linear Classification
• Lattice Fusion Networks for Image Denoising
• Resolving the cybersecurity Data Sharing Paradox to scale up cybersecurity via a co-production approach towards data sharing
• Deep Learning for Recognizing Mobile Targets in Satellite Imagery
• Self-supervised asymmetric deep hashing with margin-scalable constraint
• Deep Point-wise Prediction for Action Temporal Proposal
• Recognition of Russian traffic signs in winter conditions. Solutions of the "Ice Vision" competition winners
• OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
• Weakly Supervised Localization Using Background Images
• Gaussian Temporal Awareness Networks for Action Localization
• Semi-Automatic Annotation For Visual Object Tracking
• Self-Adaptive Reconfigurable Arrays (SARA): Using ML to Assist Scaling GEMM Acceleration
• A DCNN-based Arbitrarily-Oriented Object Detector for Quality Control and Inspection Application
• POD: Practical Object Detection with Scale-Sensitive Network
• Hands-on Guidance for Distilling Object Detectors
• Stack-VS: Stacked Visual-Semantic Attention for Image Caption Generation
• Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering
• GPNAS: A Neural Network Architecture Search Framework Based on Graphical Predictor
• Scene-based Factored Attention for Image Captioning
• Generation and Simulation of Yeast Microscopy Imagery with Deep Learning
• HishabNet: Detection, Localization and Calculation of Handwritten Bengali Mathematical Expressions
• Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations
• Adaptive Binary-Ternary Quantization
• Revisiting the Loss Weight Adjustment in Object Detection
• USB: Universal-Scale Object Detection Benchmark
• Efficient Online Transfer Learning for 3D Object Classification in Autonomous Driving
• Universal Physical Camouflage Attacks on Object Detectors
• Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
• Training Deep Neural Networks via Branch-and-Bound
• Robotic Waste Sorter with Agile Manipulation and Quickly Trainable Detector
• Opening up Open-World Tracking
• VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks
• Few-Shot Video Object Detection
• Image Segmentation, Compression and Reconstruction from Edge Distribution Estimation with Random Field and Random Cluster Theories
• Plot and Rework: Modeling Storylines for Visual Storytelling
• FishNet: A Camera Localizer using Deep Recurrent Networks
• CUAB: Convolutional Uncertainty Attention Block Enhanced the Chest X-ray Image Analysis
• Human Object Interaction Detection using Two-Direction Spatial Enhancement and Exclusive Object Prior
• T-EMDE: Sketching-based global similarity for cross-modal retrieval
• Instance-aware Remote Sensing Image Captioning with Cross-hierarchy Attention
• Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment
• Wearable Travel Aid for Environment Perception and Navigation of Visually Impaired People
• Distilling Image Classifiers in Object Detectors
• Place recognition survey: An update on deep learning approaches
• Goal-oriented Object Importance Estimation in On-road Driving Videos
• Class agnostic moving target detection by color and location prediction of moving area
• Deep Bregman Divergence for Contrastive Learning of Visual Representations
• Partially-Supervised Novel Object Captioning Leveraging Context from Paired Data
• StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation
• GoG: Relation-aware Graph-over-Graph Network for Visual Dialog
• ISyNet: Convolutional Neural Networks design for AI accelerator
• LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation
• Recognizing Part Attributes with Insufficient Data
• Sequential Voting with Relational Box Fields for Active Object Detection
• Knowledge-driven Active Learning
• SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval
• TraVLR: Now You See It, Now You Don't! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning
• Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention
• A Survey on Green Deep Learning
• Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture
• Unsupervised Spiking Instance Segmentation on Event Data using STDP
• Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
• Visual-Relation Conscious Image Generation from Structured-Text
• Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
• ScarfNet: Multi-scale Features with Deeply Fused and Redistributed Semantics for Enhanced Object Detection
• Realistic simulation of users for IT systems in cyber ranges
• Automated Detection of Patients in Hospital Video Recordings
• NoFADE: Analyzing Diminishing Returns on CO2 Investment
• Attention-based Feature Decomposition-Reconstruction Network for Scene Text Detection
• Flood Analytics Information System (FAIS) Version 4.00 Manual
• Semi-Supervised Surface Anomaly Detection of Composite Wind Turbine Blades From Drone Imagery
• Human-Object Interaction Detection via Weak Supervision
• Object-Centric Unsupervised Image Captioning
• Object Detection in Specific Traffic Scenes using YOLOv2
• Can neural networks count digit frequency?
• Predictive Ensemble Learning with Application to Scene Text Detection
• Open-set 3D Object Detection
• Vision Pair Learning: An Efficient Training Framework for Image Classification
• Document Dewarping with Control Points
• Implicit Label Augmentation on Partially Annotated Clips via Temporally-Adaptive Features Learning
• A Wireless-Vision Dataset for Privacy Preserving Human Activity Recognition
• MVB: A Large-Scale Dataset for Baggage Re-Identification and Merged Siamese Networks
• Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight
• Attention Filtering for Multi-person Spatiotemporal Action Detection on Deep Two-Stream CNN Architectures
• Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics
• Soccer Player Tracking in Low Quality Video
• DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications
• Issues in Object Detection in Videos using Common Single-Image CNNs
• PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery
• Dual Normalization Multitasking for Audio-Visual Sounding Object Localization
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
• PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attack
• Transferable Adversarial Examples for Anchor Free Object Detection
• Not Only Look But Observe: Variational Observation Model of Scene-Level 3D Multi-Object Understanding for Probabilistic SLAM
• Understanding top-down attention using task-oriented ablation design
• Labeled Data Generation with Inexact Supervision
• Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter
• ShuffleBlock: Shuffle to Regularize Deep Convolutional Neural Networks
• Region Refinement Network for Salient Object Detection
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration
• A Framework for Real-time Traffic Trajectory Tracking, Speed Estimation, and Driver Behavior Calibration at Urban Intersections Using Virtual Traffic Lanes
• Generation and frame characteristics of predefined evenly-distributed class centroids for pattern classification
• SRPN: similarity-based region proposal networks for nuclei and cells detection in histology images
• Building Intelligent Autonomous Navigation Agents
• Real-time 3D Object Detection using Feature Map Flow
• Learning from Web Data with Self-Organizing Memory Module
• Adventurer's Treasure Hunt: A Transparent System for Visually Grounded Compositional Visual Question Answering based on Scene Graphs
• SRF-Net: Selective Receptive Field Network for Anchor-Free Temporal Action Detection
• Doing good by fighting fraud: Ethical anti-fraud systems for mobile payments
• Integration of Text-maps in Convolutional Neural Networks for Region Detection among Different Textual Categories
• Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization
• Semantics to Space(S2S): Embedding semantics into spatial space for zero-shot verb-object query inferencing
• A Transductive Maximum Margin Classifier for Few-Shot Learning
• Automated Object Behavioral Feature Extraction for Potential Risk Analysis based on Video Sensor
• Integrating Deep Learning and Augmented Reality to Enhance Situational Awareness in Firefighting Environments
• Case Relation Transformer: A Crossmodal Language Generation Model for Fetching Instructions
• CompConv: A Compact Convolution Module for Efficient Feature Learning
• Merging Tasks for Video Panoptic Segmentation
• Doctor of Crosswise: Reducing Over-parametrization in Neural Networks
• CS-R-FCN: Cross-supervised Learning for Large-Scale Object Detection
• Bidirectional Regression for Arbitrary-Shaped Text Detection
• Semantically-Aware Strategies for Stereo-Visual Robotic Obstacle Avoidance
• FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange
• Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos
• Geometric Data Augmentation Based on Feature Map Ensemble
• Multi-stage Pre-training over Simplified Multimodal Pre-training Models
• United We Learn Better: Harvesting Learning Improvements From Class Hierarchies Across Tasks
• Domain Adaptor Networks for Hyperspectral Image Recognition
• Double-Dot Network for Antipodal Grasp Detection
• Neural Twins Talk & Alternative Calculations
• Two is a crowd: tracking relations in videos
• Identifying and Exploiting Structures for Reliable Deep Learning
• Hardware realisation of nonlinear dynamical systems for and from biology
• Leveraging Orientation for Weakly Supervised Object Detection with Application to Firearm Localization
• Exploring Data Aggregation and Transformations to Generalize across Visual Domains
• OOWL500: Overcoming Dataset Collection Bias in the Wild
• Improving Object Detection and Attribute Recognition by Feature Entanglement Reduction
• Target-Tailored Source-Transformation for Scene Graph Generation
• Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training
• Layer-wise Customized Weak Segmentation Block and AIoU Loss for Accurate Object Detection
• PR Product: A Substitute for Inner Product in Neural Networks
• Densely Semantic Enhancement for Domain Adaptive Region-free Detectors
• AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks
• Architecture Aware Latency Constrained Sparse Neural Networks
• Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers
• Temporal RoI Align for Video Object Recognition
• Multi-Scale Aligned Distillation for Low-Resolution Detection
• Fast query-by-example speech search using separable model
• Learning Natural Language Generation from Scratch
• COVR: A test-bed for Visually Grounded Compositional Generalization with real images
• MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets
• EllipseNet: Anchor-Free Ellipse Detection for Automatic Cardiac Biometrics in Fetal Echocardiography
• $f$-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception
• Turning old models fashion again: Recycling classical CNN networks using the Lattice Transformation
• Adversarial Semantic Contour for Object Detection
• CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
• Deep Learning Approach Protecting Privacy in Camera-Based Critical Applications
• CNN-based Human Detection for UAVs in Search and Rescue
• Learning Single/Multi-Attribute of Object with Symmetry and Group
• Multi-Precision Quantized Neural Networks via Encoding Decomposition of -1 and +1
• Learning Deep Image Priors for Blind Image Denoising
• Topic Scene Graph Generation by Attention Distillation from Caption
• Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization
• Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation
• ASK: Adaptively Selecting Key Local Features for RGB-D Scene Recognition
• Self-Supervised Object Detection via Generative Image Synthesis
• Mitosis Detection for Breast Cancer Pathology Images Using UV-Net
• NAS-FCOS: Efficient Search for Object Detection Architectures
• CoopSubNet: Cooperating Subnetwork for Data-Driven Regularization of Deep Networks under Limited Training Budgets
• Generative Residual Attention Network for Disease Detection
• AlteregoNets: a way to human augmentation
• Continuous Trade-off Optimization between Fast and Accurate Deep Face Detectors
• CBIR using Pre-Trained Neural Networks
• PolyTrack: Tracking with Bounding Polygons
• Learned Image Compression for Machine Perception
• Bootstrap Your Object Detector via Mixed Training
• Frustum Fusion: Pseudo-LiDAR and LiDAR Fusion for 3D Detection
• $P^2$ Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation
• Fast Local Attack: Generating Local Adversarial Examples for Object Detectors
• Spatial-temporal Fusion Convolutional Neural Network for Simulated Driving Behavior Recognition
• Adversarial Domain Randomization
• Efficient Pipelines for Vision-Based Context Sensing
• DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection
• Transformation Driven Visual Reasoning
• Fast Object Detection with Latticed Multi-Scale Feature Fusion
• Stereo Frustums: A Siamese Pipeline for 3D Object Detection
• Automated data extraction of bar chart raster images
• GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts
• Data-efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions
• FPAENet: Pneumonia Detection Network Based on Feature Pyramid Attention Enhancement
• Context Encoding Chest X-rays
• Unsupervised Part Discovery via Feature Alignment
• A Hypergradient Approach to Robust Regression without Correspondence
• Towards Part-Based Understanding of RGB-D Scans
• Copyspace: Where to Write on Images?
• Discovering Spatio-Temporal Action Tubes
• PCGAN: Partition-Controlled Human Image Generation
• Learning to Generate Content-Aware Dynamic Detectors
• DeepKey: Towards End-to-End Physical Key Replication From a Single Photograph
• Robust Real-Time Pedestrian Detection on Embedded Devices
• Smoothed Gaussian Mixture Models for Video Classification and Recommendation
• Dense Multiscale Feature Fusion Pyramid Networks for Object Detection in UAV-Captured Images
• Impoved RPN for Single Targets Detection based on the Anchor Mask Net
• AmphibianDetector: adaptive computation for moving objects detection
• Research on Fast Text Recognition Method for Financial Ticket Image
• Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data Augmentation
• Adaptive Remote Sensing Image Attribute Learning for Active Object Detection
• Shape Back-Projection In 3D Scenes
• Semi Supervised Deep Quick Instance Detection and Segmentation
• Multi-Task Network Pruning and Embedded Optimization for Real-time Deployment in ADAS
• Online Active Proposal Set Generation for Weakly Supervised Object Detection
• Hierarchical Graph-RNNs for Action Detection of Multiple Activities
• Discovering Multi-Label Actor-Action Association in a Weakly Supervised Setting
• Evolution Attack On Neural Networks
• Provident Vehicle Detection at Night: The PVDN Dataset
• A Unified Light Framework for Real-time Fault Detection of Freight Train Images
• Cross Chest Graph for Disease Diagnosis with Structural Relational Reasoning
• Multi-Attribute Enhancement Network for Person Search
• Custom Object Detection via Multi-Camera Self-Supervised Learning
• APEX-Net: Automatic Plot Extractor Network
• Analysing object detectors from the perspective of co-occurring object categories
• MASON: A Model AgnoStic ObjectNess Framework
• Anchor Distance for 3D Multi-Object Distance Estimation from 2D Single Shot
• Towards Large-Scale Video Video Object Mining
• OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks
• Phase Space Reconstruction Network for Lane Intrusion Action Recognition
• Relationship-based Neural Baby Talk
• Robust 2D/3D Vehicle Parsing in CVIS
• Sim-to-Real Transfer of Robot Learning with Variable Length Inputs
• Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection
• The Case for High-Accuracy Classification: Think Small, Think Many!
• Neural Task Planning with And-Or Graph Representations
• Structure-Aware Face Clustering on a Large-Scale Graph with $10^7$ Nodes
• Picasso: A CUDA-based Library for Deep Learning over 3D Meshes
• A Multiplexed Network for End-to-End, Multilingual OCR
• Knowledge Distillation By Sparse Representation Matching
• Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition
• Two-phase weakly supervised object detection with pseudo ground truth mining
• Malignancy Prediction and Lesion Identification from Clinical Dermatological Images
• Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories
• Fingerspelling Detection in American Sign Language
• Deep Online Fused Video Stabilization
• Visual Tracking via Reliable Memories
• TraMNet - Transition Matrix Network for Efficient Action Tube Proposals
• Few-Shot Transformation of Common Actions into Time and Space
• Learning Spatial Context with Graph Neural Network for Multi-Person Pose Grouping
• AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks
• Weakly Supervised Object Localization and Detection: A Survey
• Error-Corrected Margin-Based Deep Cross-Modal Hashing for Facial Image Retrieval
• LU-Net: a multi-task network to improve the robustness of segmentation of left ventriclular structures by deep learning in 2D echocardiography
• End-to-End Learning via a Convolutional Neural Network for Cancer Cell Line Classification
• MA 3 : Model Agnostic Adversarial Augmentation for Few Shot learning
• Training few-shot classification via the perspective of minibatch and pretraining
• Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations
• Intelligent Orchestration of ADAS Pipelines on Next Generation Automotive Platforms
• Spatially Attentive Output Layer for Image Classification
• CPARR: Category-based Proposal Analysis for Referring Relationships
• MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network
• Generative Adversarial Networks for Unsupervised Object Co-localization
• Instance Segmentation of Biomedical Images with an Object-aware Embedding Learned with Local Constraints
• A Revised Generative Evaluation of Visual Dialogue
• Long Activity Video Understanding using Functional Object-Oriented Network
• Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios
• Cross-Modality Relevance for Reasoning on Language and Vision
• Anchors Based Method for Fingertips Position Estimation from a Monocular RGB Image using Deep Neural Network
• Ventral-Dorsal Neural Networks: Object Detection via Selective Attention
• A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection
• Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models
• KL-Divergence-Based Region Proposal Network for Object Detection
• Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation
• DeepFirearm: Learning Discriminative Feature Representation for Fine-grained Firearm Retrieval
• The Research of the Real-time Detection and Recognition of Targets in Streetscape Videos
• Delving into the Imbalance of Positive Proposals in Two-stage Object Detection
• Accelerating Neural Network Inference by Overflow Aware Quantization
• Condensing Two-stage Detection with Automatic Object Key Part Discovery
• End-to-end Learning for Inter-Vehicle Distance and Relative Velocity Estimation in ADAS with a Monocular Camera
• Physics-based Scene-level Reasoning for Object Pose Estimation in Clutter
• Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
• Sequential Feature Filtering Classifier
• Off-Policy Self-Critical Training for Transformer in Visual Paragraph Generation
• Orthogonal Deep Models As Defense Against Black-Box Attacks
• Motion Prediction in Visual Object Tracking
• A Few-Shot Sequential Approach for Object Counting
• A Classification approach towards Unsupervised Learning of Visual Representations