YOLOv3: An Incremental Improvement

Abstract

We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more accurate. It's still fast though, don't worry. At 320x320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 mAP@50 in 51 ms on a Titan X, compared to 57.5 mAP@50 in 198 ms by RetinaNet, similar performance but 3.8x faster. As always, all the code is online at https://pjreddie.com/yolo/

Tech Report

References in corpus (6)

• Deep Residual Learning for Image Recognition
• DSSD : Deconvolutional Single Shot Detector
• Focal Loss for Dense Object Detection
• Feature Pyramid Networks for Object Detection
• YOLO9000: Better, Faster, Stronger
• Beyond Skip Connections: Top-Down Modulation for Object Detection

Cited by in corpus (1010)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• YOLOX: Exceeding YOLO Series in 2021
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• A Survey of Deep Learning Techniques for Autonomous Driving
• A Survey of Deep Learning-based Object Detection
• Gliding vertex on the horizontal bounding box for multi-oriented object detection
• 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
• FCOS: Fully Convolutional One-Stage Object Detection
• Deep Learning in Video Multi-Object Tracking: A Survey
• Object Detection in 20 Years: A Survey
• Binary Neural Networks: A Survey
• YOLACT++: Better Real-time Instance Segmentation
• EfficientDet: Scalable and Efficient Object Detection
• Deep Learning for Chest X-ray Analysis: A Survey
• Learning Spatial Fusion for Single-Shot Object Detection
• Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
• Deep Learning for UAV-based Object Detection and Tracking: A Survey
• CSPNet: A New Backbone that can Enhance Learning Capability of CNN
• The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
• Satellite Pose Estimation Challenge: Dataset, Competition Design and Results
• Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
• AdvHat: Real-world adversarial attack on ArcFace Face ID system
• Combining EfficientNet and Vision Transformers for Video Deepfake Detection
• A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
• Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics
• 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 Smart, Efficient, and Reliable Parking Surveillance System with Edge Artificial Intelligence on IoT Devices
• PP-YOLO: An Effective and Efficient Implementation of Object Detector
• Multi-Object Representation Learning with Iterative Variational Inference
• RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization
• Fruit Detection, Segmentation and 3D Visualisation of Environments in Apple Orchards
• A survey on Semi-, Self- and Unsupervised Learning for Image Classification
• An Efficient and Layout-Independent Automatic License Plate Recognition System Based on the YOLO detector
• Real-Time Apple Detection System Using Embedded Systems With Hardware Accelerators: An Edge AI Application
• Artificial Intelligence for Satellite Communication: A Review
• You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
• AutoAssign: Differentiable Label Assignment for Dense Object Detection
• A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video
• Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse
• Visual Identification of Individual Holstein-Friesian Cattle via Deep Metric Learning
• Real-time object detection method based on improved YOLOv4-tiny
• Bringing AI To Edge: From Deep Learning's Perspective
• Enabling and Emerging Technologies for Social Distancing: A Comprehensive Survey and Open Problems
• CornerNet-Lite: Efficient Keypoint Based Object Detection
• PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
• Probabilistic two-stage detection
• Scalable Image Coding for Humans and Machines
• Efficient DETR: Improving End-to-End Object Detector with Dense Prior
• Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery
• Semantic Object Accuracy for Generative Text-to-Image Synthesis
• Decentralized Visual-Inertial-UWB Fusion for Relative State Estimation of Aerial Swarm
• Mobile Augmented Reality: User Interfaces, Frameworks, and Intelligence
• DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
• Bag of Freebies for Training Object Detection Neural Networks
• RepPoints: Point Set Representation for Object Detection
• Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
• Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?
• TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecasting
• A deep learning framework for quality assessment and restoration in video endoscopy
• Real-Time Fruit Recognition and Grasping Estimation for Autonomous Apple Harvesting
• LIFT-SLAM: a deep-learning feature-based monocular visual SLAM method
• JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environments
• Scaled-YOLOv4: Scaling Cross Stage Partial Network
• A Fusion Adversarial Underwater Image Enhancement Network with a Public Test Dataset
• Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss
• TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
• RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free
• R${}^3$-Net: A Deep Network for Multi-oriented Vehicle Detection in Aerial Images and Videos
• XNOR-Net++: Improved Binary Neural Networks
• Adapting Mask-RCNN for Automatic Nucleus Segmentation
• On Physical Adversarial Patches for Object Detection
• Analysis of the hands in egocentric vision: A survey
• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• ByteTrack: Multi-Object Tracking by Associating Every Detection Box
• UWGAN: Underwater GAN for Real-world Underwater Color Restoration and Dehazing
• Bottom-up Object Detection by Grouping Extreme and Center Points
• Deep Learning-based Spacecraft Relative Navigation Methods: A Survey
• A System for Automatic Rice Disease Detection from Rice Paddy Images Serviced via a Chatbot
• Large-scale Autonomous Flight with Real-time Semantic SLAM under Dense Forest Canopy
• PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images
• Pose-Aware Instance Segmentation Framework from Cone Beam CT Images for Tooth Segmentation
• ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
• Layer-specific Optimization for Mixed Data Flow with Mixed Precision in FPGA Design for CNN-based Object Detectors
• A Bayesian Filter for Multi-view 3D Multi-object Tracking with Occlusion Handling
• Aerial Images Processing for Car Detection using Convolutional Neural Networks: Comparison between Faster R-CNN and YoloV3
• Self-supervised Image Enhancement Network: Training with Low Light Images Only
• Pedestrian Models for Autonomous Driving Part I: Low-Level Models, from Sensing to Tracking
• LittleYOLO-SPP: A Delicate Real-Time Vehicle Detection Algorithm
• PP-YOLOv2: A Practical Object Detector
• Multimodal Spatio-Temporal Deep Learning Approach for Neonatal Postoperative Pain Assessment
• AP-Loss for Accurate One-Stage Object Detection
• Scale-Aware Trident Networks for Object Detection
• Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation
• An overview of mixing augmentation methods and augmentation strategies
• Orthographic Feature Transform for Monocular 3D Object Detection
• A Real-Time Wrong-Way Vehicle Detection Based on YOLO and Centroid Tracking
• A Deep Learning Based Automatic Defect Analysis Framework for In-situ TEM Ion Irradiations
• AVDNet: A Small-Sized Vehicle Detection Network for Aerial Visual Data
• Towards Goal-Oriented Semantic Signal Processing: Applications and Future Challenges
• Support Vector Machine and YOLO for a Mobile Food Grading System
• Traffic Light Recognition Using Deep Learning and Prior Maps for Autonomous Cars
• Handgun detection using combined human pose and weapon appearance
• Learning to Generate Diverse Dance Motions with Transformer
• All-In-One Underwater Image Enhancement using Domain-Adversarial Learning
• Referring Transformer: A One-step Approach to Multi-task Visual Grounding
• LEEP: A New Measure to Evaluate Transferability of Learned Representations
• Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation
• Graph Neural Networks for Natural Language Processing: A Survey
• EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach
• Real-World Image Datasets for Federated Learning
• TinaFace: Strong but Simple Baseline for Face Detection
• Gradient Harmonized Single-stage Detector
• Optimizing Rank-based Metrics with Blackbox Differentiation
• One-Shot Instance Segmentation
• Generative adversarial network with object detector discriminator for enhanced defect detection on ultrasonic B-scans
• Revisiting Feature Alignment for One-stage Object Detection
• Multi-Scale Boosted Dehazing Network with Dense Feature Fusion
• A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization
• 6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning
• A Survey of Deep Learning for Scientific Discovery
• A Survey on Deep Domain Adaptation for LiDAR Perception
• HEU Emotion: A Large-scale Database for Multi-modal Emotion Recognition in the Wild
• Towards Image-based Automatic Meter Reading in Unconstrained Scenarios: A Robust and Efficient Approach
• COVID-Robot: Monitoring Social Distancing Constraints in Crowded Scenarios
• Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses
• Multi-Scale Progressive Fusion Network for Single Image Deraining
• Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison
• DEFT: Detection Embeddings for Tracking
• Learn an Effective Lip Reading Model without Pains
• Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
• Adversarial Examples in Modern Machine Learning: A Review
• Enhancing Object Detection for Autonomous Driving by Optimizing Anchor Generation and Addressing Class Imbalance
• s-LWSR: Super Lightweight Super-Resolution Network
• A Comprehensive Safety Metric to Evaluate Perception in Autonomous Systems
• Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection
• Deep Learning based Virtual Point Tracking for Real-Time Target-less Dynamic Displacement Measurement in Railway Applications
• Optimized and autonomous machine learning framework for characterizing pores, particles, grains and grain boundaries in microstructural images
• Traffic-Aware Multi-Camera Tracking of Vehicles Based on ReID and Camera Link Model
• An Active Sense and Avoid System for Flying Robots in Dynamic Environments
• TNCR: Table Net Detection and Classification Dataset
• LFFD: A Light and Fast Face Detector for Edge Devices
• ThunderNet: Towards Real-time Generic Object Detection
• The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion
• AugFPN: Improving Multi-scale Feature Learning for Object Detection
• CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
• A cow structural model for video analytics of cow health
• ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks
• Multi-adversarial Faster-RCNN for Unrestricted Object Detection
• YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers
• Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds
• A Vision-based Social Distancing and Critical Density Detection System for COVID-19
• Rethinking Classification and Localization for Object Detection
• D${}^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios
• YOLO5Face: Why Reinventing a Face Detector
• Real-time automatic polyp detection in colonoscopy using feature enhancement module and spatiotemporal similarity correlation unit
• Sequence Level Semantics Aggregation for Video Object Detection
• EGO-CH: Dataset and Fundamental Tasks for Visitors BehavioralUnderstanding using Egocentric Vision
• Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation
• FCOS: A simple and strong anchor-free object detector
• A Robust Illumination-Invariant Camera System for Agricultural Applications
• CATCH: Characterizing and Tracking Colloids Holographically using deep neural networks
• Fine-Grained Crowd Counting
• Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation
• Fast object detection in compressed JPEG Images
• RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
• EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
• UG${}^{2+}$ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments
• Objects detection for remote sensing images based on polar coordinates
• Can WiFi Estimate Person Pose?
• Daedalus: Breaking Non-Maximum Suppression in Object Detection via Adversarial Examples
• A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
• Multi-Task Incremental Learning for Object Detection
• Pareto-Optimal Bit Allocation for Collaborative Intelligence
• AP-MTL: Attention Pruned Multi-task Learning Model for Real-time Instrument Detection and Segmentation in Robot-assisted Surgery
• VarifocalNet: An IoU-aware Dense Object Detector
• EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments
• Towards Real-Time Multi-Object Tracking
• Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence
• Interpreting Black Box Models via Hypothesis Testing
• PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
• Track Boosting and Synthetic Data Aided Drone Detection
• Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network
• Exploring Object Relation in Mean Teacher for Cross-Domain Detection
• Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Models
• Generating Multiple Objects at Spatially Distinct Locations
• Impedance-optical Dual-modal Cell Culture Imaging with Learning-based Information Fusion
• FedVision: An Online Visual Object Detection Platform Powered by Federated Learning
• Collaborative Multi-Robot Systems for Search and Rescue: Coordination and Perception
• CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
• Universal Adversarial Perturbations: A Survey
• The Indirect Convolution Algorithm
• SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbations
• Unbiased Teacher for Semi-Supervised Object Detection
• (AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network
• Dynamic Adversarial Patch for Evading Object Detection Models
• Computer Stereo Vision for Autonomous Driving
• RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices
• FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network
• Light-Weight RetinaNet for Object Detection
• The Cube++ Illumination Estimation Dataset
• Multi-View Object Pose Refinement With Differentiable Renderer
• Simple Training Strategies and Model Scaling for Object Detection
• Chainer: A Deep Learning Framework for Accelerating the Research Cycle
• CityFlow-NL: Tracking and Retrieval of Vehicles at City Scale by Natural Language Descriptions
• Real-Time Referring Expression Comprehension by Single-Stage Grounding Network
• Effect of Annotation Errors on Drone Detection with YOLOv3
• Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systems
• A Survey of Deep Learning Approaches for OCR and Document Understanding
• YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design
• CSL-YOLO: A New Lightweight Object Detection System for Edge Computing
• Computing Systems for Autonomous Driving: State-of-the-Art and Challenges
• Recognizing Characters in Art History Using Deep Learning
• PerceMon: Online Monitoring for Perception Systems
• Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
• Autonomous and cooperative design of the monitor positions for a team of UAVs to maximize the quantity and quality of detected objects
• Uncertainty-based Modulation for Lifelong Learning
• Detection in Crowded Scenes: One Proposal, Multiple Predictions
• Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments
• LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
• Estimating 6D Pose From Localizing Designated Surface Keypoints
• SA-Net: Deep Neural Network for Robot Trajectory Recognition from RGB-D Streams
• Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
• Towards Robust Learning-Based Pose Estimation of Noncooperative Spacecraft
• NAS-FCOS: Fast Neural Architecture Search for Object Detection
• A fast and efficient deep learning procedure for tracking droplet motion in dense microfluidic emulsions
• CTU Depth Decision Algorithms for HEVC: A Survey
• Mediastinal lymph nodes segmentation using 3D convolutional neural network ensembles and anatomical priors guiding
• Deep-RBF Networks Revisited: Robust Classification with Rejection
• Towards Palmprint Verification On Smartphones
• A Fast and Accurate One-Stage Approach to Visual Grounding
• Traffic Surveillance using Vehicle License Plate Detection and Recognition in Bangladesh
• White blood cell subtype detection and classification
• QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
• Improving Target-driven Visual Navigation with Attention on 3D Spatial Relationships
• SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
• Embodied Visual Recognition
• Active and Incremental Learning with Weak Supervision
• Active Terahertz Imaging Dataset for Concealed Object Detection
• Decentralized Spatial-Temporal Trajectory Planning for Multicopter Swarms
• Focal and Global Knowledge Distillation for Detectors
• NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge
• Knowledge driven Description Synthesis for Floor Plan Interpretation
• Butterfly Detection and Classification Based on Integrated YOLO Algorithm
• MilliTRACE-IR: Contact Tracing and Temperature Screening via mm-Wave and Infrared Sensing
• Consistent Optimization for Single-Shot Object Detection
• Anchor Pruning for Object Detection
• Computation-Communication Trade-offs and Sensor Selection in Real-time Estimation for Processing Networks
• Stereo Camera Visual SLAM with Hierarchical Masking and Motion-state Classification at Outdoor Construction Sites Containing Large Dynamic Objects
• Intrinsic Relationship Reasoning for Small Object Detection
• CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
• Global Wheat Head Detection (GWHD) dataset: a large and diverse dataset of high resolution RGB labelled images to develop and benchmark wheat head detection methods
• Towards Universal Object Detection by Domain Attention
• Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object Tracking
• Cardiac Segmentation on CT Images through Shape-Aware Contour Attentions
• Comparison of State-of-the-Art Deep Learning APIs for Image Multi-Label Classification using Semantic Metrics
• Deep4Air: A Novel Deep Learning Framework for Airport Airside Surveillance
• Self-supervised Low Light Image Enhancement and Denoising
• Bridge Damage Detection using a Single-Stage Detector and Field Inspection Images
• RGB Stream Is Enough for Temporal Action Detection
• Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes
• Dual Refinement Feature Pyramid Networks for Object Detection
• Joint Detection and Tracking in Videos with Identification Features
• Implementation of UAV Coordination Based on a Hierarchical Multi-UAV Simulation Platform
• Cooperating RPN's Improve Few-Shot Object Detection
• Human-Perception-Oriented Pseudo Analog Video Transmissions with Deep Learning
• Identify Light-Curve Signals with Deep Learning Based Object Detection Algorithm. I. Transit Detection
• Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
• Improving One-stage Visual Grounding by Recursive Sub-query Construction
• DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
• iTV: Inferring Traffic Violation-Prone Locations with Vehicle Trajectories and Road Environment Data
• Driving Datasets Literature Review
• Metamorphic Testing for Object Detection Systems
• Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
• Few-shot Object Detection via Feature Reweighting
• Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing
• Seeing isn't Believing: Practical Adversarial Attack Against Object Detectors
• Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation
• A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learning
• MOTR: End-to-End Multiple-Object Tracking with Transformer
• RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation
• Segmentation-Aware Image Denoising without Knowing True Segmentation
• ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
• Over-sampling De-occlusion Attention Network for Prohibited Items Detection in Noisy X-ray Images
• Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts
• CenterFace: Joint Face Detection and Alignment Using Face as Point
• FCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection
• Objects in Semantic Topology
• Metamorphic Detection of Adversarial Examples in Deep Learning Models With Affine Transformations
• Anchor Box Optimization for Object Detection
• Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN
• Domain Adaptive YOLO for One-Stage Cross-Domain Detection
• MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding
• Additive Noise Annealing and Approximation Properties of Quantized Neural Networks
• Cascaded Structure Tensor Framework for Robust Identification of Heavily Occluded Baggage Items from X-ray Scans
• EdgeNet: Balancing Accuracy and Performance for Edge-based Convolutional Neural Network Object Detectors
• REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs
• Underwater Fish Detection using Deep Learning for Water Power Applications
• IoU-aware Single-stage Object Detector for Accurate Localization
• Fully Automatic Wound Segmentation with Deep Convolutional Neural Networks
• End-to-End Object Detection with Fully Convolutional Network
• Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
• Attention Neural Network for Trash Detection on Water Channels
• M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network
• Linguistically-aware Attention for Reducing the Semantic-Gap in Vision-Language Tasks
• A Comparative Review of Recent Few-Shot Object Detection Algorithms
• Rethinking Channel Dimensions for Efficient Model Design
• BdSL36: A Dataset for Bangladeshi Sign Letters Recognition
• SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
• Structure-Aware Completion of Photogrammetric Meshes in Urban Road Environment
• Efficient Differentiable Neural Architecture Search with Meta Kernels
• Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
• Detection and Tracking Meet Drones Challenge
• Dynamic Refinement Network for Oriented and Densely Packed Object Detection
• Machine Learning Based Analysis of Finnish World War II Photographers
• FOD-A: A Dataset for Foreign Object Debris in Airports
• Dynamic backdoor attacks against federated learning
• Instance Segmentation with Point Supervision
• Cross-Modal Graph with Meta Concepts for Video Captioning
• Perspective-corrected Spatial Referring Expression Generation for Human-Robot Interaction
• Salience Biased Loss for Object Detection in Aerial Images
• WQT and DG-YOLO: towards domain generalization in underwater object detection
• Occluded Prohibited Items Detection: an X-ray Security Inspection Benchmark and De-occlusion Attention Module
• ALERT: Accurate Learning for Energy and Timeliness
• BabyNet: A Lightweight Network for Infant Reaching Action Recognition in Unconstrained Environments to Support Future Pediatric Rehabilitation Applications
• Few-Shot Learning for Road Object Detection
• OpenEI: An Open Framework for Edge Intelligence
• Kidney Recognition in CT Using YOLOv3
• TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems
• Visual Relationship Detection using Scene Graphs: A Survey
• Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes
• LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image
• Deep Active Learning for Remote Sensing Object Detection
• Real-Time Face & Eye Tracking and Blink Detection using Event Cameras
• MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
• A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video
• Efficient Poverty Mapping using Deep Reinforcement Learning
• Progressive Localization Networks for Language-based Moment Localization
• VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
• Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
• Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System
• Go Fetch: Mobile Manipulation in Unstructured Environments
• Towards Performance Clarity of Edge Video Analytics
• Improving Automated Sonar Video Analysis to Notify About Jellyfish Blooms
• CoVA: Context-aware Visual Attention for Webpage Information Extraction
• Locate then Segment: A Strong Pipeline for Referring Image Segmentation
• Hallucination Improves Few-Shot Object Detection
• Automatic lesion segmentation and Pathological Myopia classification in fundus images
• Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-Time
• Sentiment Analysis of Fashion Related Posts in Social Media
• Guided Attention Network for Object Detection and Counting on Drones
• Underwater object detection using Invert Multi-Class Adaboost with deep learning
• An Orientation Factor for Object-Oriented SLAM
• On Learning Vehicle Detection in Satellite Video
• ODIN: Automated Drift Detection and Recovery in Video Analytics
• Learning More with Less: GAN-based Medical Image Augmentation
• Detecting Frames in News Headlines and Lead Images in U.S. Gun Violence Coverage
• Explicit Shape Encoding for Real-Time Instance Segmentation
• A Software Architecture for Autonomous Vehicles: Team LRM-B Entry in the First CARLA Autonomous Driving Challenge
• Attention-based Joint Detection of Object and Semantic Part
• Object detection on aerial imagery using CenterNet
• Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization
• A General Framework of Learning Multi-Vehicle Interaction Patterns from Videos
• LookOut! Interactive Camera Gimbal Controller for Filming Long Takes
• Improving CNN-based Planar Object Detection with Geometric Prior Knowledge
• Affinity LCFCN: Learning to Segment Fish with Weak Supervision
• Multi-Cue Vehicle Detection for Semantic Video Compression In Georegistered Aerial Videos
• Learning on Hardware: A Tutorial on Neural Network Accelerators and Co-Processors
• Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
• Multi-level Domain Adaptive learning for Cross-Domain Detection
• FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery
• Casualty Detection from 3D Point Cloud Data for Autonomous Ground Mobile Rescue Robots
• BAF-Detector: An Efficient CNN-Based Detector for Photovoltaic Cell Defect Detection
• Oriented RepPoints for Aerial Object Detection
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Deep neural networks approach to microbial colony detection -- a comparative analysis
• Towards navigation without precise localization: Weakly supervised learning of goal-directed navigation cost map
• Efficient Golf Ball Detection and Tracking Based on Convolutional Neural Networks and Kalman Filter
• A Computer Vision Based Beamforming Scheme for Millimeter Wave Communication in LOS Scenarios
• DeFog: Fog Computing Benchmarks
• Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding
• Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation
• Segmentation-driven 6D Object Pose Estimation
• SQuantizer: Simultaneous Learning for Both Sparse and Low-precision Neural Networks
• ModelHub.AI: Dissemination Platform for Deep Learning Models
• Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approach
• Matching Representations of Explainable Artificial Intelligence and Eye Gaze for Human-Machine Interaction
• On the Road with 16 Neurons: Mental Imagery with Bio-inspired Deep Neural Networks
• Face Detection with Feature Pyramids and Landmarks
• AGE Challenge: Angle Closure Glaucoma Evaluation in Anterior Segment Optical Coherence Tomography
• Automated Detection of Equine Facial Action Units
• Sketch2Code: Transformation of Sketches to UI in Real-time Using Deep Neural Network
• LogoDet-3K: A Large-Scale Image Dataset for Logo Detection
• Monocular, One-stage, Regression of Multiple 3D People
• TKD: Temporal Knowledge Distillation for Active Perception
• FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism
• Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction
• SMOT: Single-Shot Multi Object Tracking
• G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
• DNNVM : End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-based CNN Accelerators
• Road Damage Detection and Classification with Detectron2 and Faster R-CNN
• Image Conditioned Keyframe-Based Video Summarization Using Object Detection
• Learning a Proposal Classifier for Multiple Object Tracking
• MultiResolution Attention Extractor for Small Object Detection
• Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks
• Transform and Tell: Entity-Aware News Image Captioning
• Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects
• ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation
• Six-channel Image Representation for Cross-domain Object Detection
• Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
• Low-Power Object Counting with Hierarchical Neural Networks
• MM-FSOD: Meta and metric integrated few-shot object detection
• Iranis: A Large-scale Dataset of Farsi License Plate Characters
• LapNet : Automatic Balanced Loss and Optimal Assignment for Real-Time Dense Object Detection
• Analyzing and Improving Neural Networks by Generating Semantic Counterexamples through Differentiable Rendering
• A Real-time Global Inference Network for One-stage Referring Expression Comprehension
• Automated Detecting and Placing Road Objects from Street-level Images
• Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection
• Squeezed Deep 6DoF Object Detection Using Knowledge Distillation
• MDFN: Multi-Scale Deep Feature Learning Network for Object Detection
• Apple Defect Detection Using Deep Learning Based Object Detection For Better Post Harvest Handling
• NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection
• Decision-based Universal Adversarial Attack
• Comparison-Based Convolutional Neural Networks for Cervical Cell/Clumps Detection in the Limited Data Scenario
• Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection
• Real-Time Text Detection and Recognition
• Events-to-Video: Bringing Modern Computer Vision to Event Cameras
• A Deep Learning-Based FPGA Function Block Detection Method with Bitstream to Image Transformation
• Towards the Internet of Robotic Things: Analysis, Architecture, Components and Challenges
• A Novel Automation-Assisted Cervical Cancer Reading Method Based on Convolutional Neural Network
• Robust RGB-based 6-DoF Pose Estimation without Real Pose Annotations
• Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework
• The Problem of Fragmented Occlusion in Object Detection
• Meta-learning algorithms for Few-Shot Computer Vision
• Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark
• Spectro-Temporal RF Identification using Deep Learning
• Drowsiness Detection Based On Driver Temporal Behavior Using a New Developed Dataset
• SkyQuery: An Aerial Drone Video Sensing Platform
• OTA: Optimal Transport Assignment for 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
• Enabling Retrain-free Deep Neural Network Pruning using Surrogate Lagrangian Relaxation
• Unsupervised Video Decomposition using Spatio-temporal Iterative Inference
• Research on Mosaic Image Data Enhancement for Overlapping Ship Targets
• Rethinking Natural Adversarial Examples for Classification Models
• ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
• Towards Practical Implementations of Person Re-Identification from Full Video Frames
• PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation
• ARC: A Vision-based Automatic Retail Checkout System
• Learning the Precise Feature for Cluster Assignment
• Bring Your Own Codegen to Deep Learning Compiler
• Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention
• Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations
• Localization Distillation for Dense Object Detection
• Fooling thermal infrared pedestrian detectors in real world using small bulbs
• MeshAdv: Adversarial Meshes for Visual Recognition
• Multimodal Generative Models for Compositional Representation Learning
• Detecting The Objects on The Road Using Modular Lightweight Network
• 360-Indoor: Towards Learning Real-World Objects in 360° Indoor Equirectangular Images
• Optimizing Prediction Serving on Low-Latency Serverless Dataflow
• Robust Real-time Pedestrian Detection in Aerial Imagery on Jetson TX2
• COVID-19 personal protective equipment detection using real-time deep learning methods
• No Peeking through My Windows: Conserving Privacy in Personal Drones
• End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning
• Ground-aware Monocular 3D Object Detection for Autonomous Driving
• RTFN: A Robust Temporal Feature Network for Time Series Classification
• DENet: A Universal Network for Counting Crowd with Varying Densities and Scales
• CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis
• SWA Object Detection
• Uncertainty-Aware Voxel based 3D Object Detection and Tracking with von-Mises Loss
• Deep Learning in Computer-Aided Diagnosis and Treatment of Tumors: A Survey
• Learning to Exploit Multiple Vision Modalities by Using Grafted Networks
• Adaptive Object Detection with Dual Multi-Label Prediction
• 2nd Place Solution for Waymo Open Dataset Challenge -- Real-time 2D Object Detection
• A Spacecraft Dataset for Detection, Segmentation and Parts Recognition
• Good Practices and A Strong Baseline for Traffic Anomaly Detection
• Revisiting Knowledge Distillation for Object Detection
• Towards Real-Time Monocular Depth Estimation for Robotics: A Survey
• General Instance Distillation for Object Detection
• PAFNet: An Efficient Anchor-Free Object Detector Guidance
• Classic versus deep learning approaches to address computer vision challenges
• A Unified Framework for Generic, Query-Focused, Privacy Preserving and Update Summarization using Submodular Information Measures
• Fast Region Proposal Learning for Object Detection for Robotics
• DeepApple: Deep Learning-based Apple Detection using a Suppression Mask R-CNN
• Referring Expression Comprehension: A Survey of Methods and Datasets
• Domain-Specific Suppression for Adaptive Object Detection
• A Possible Reason for why Data-Driven Beats Theory-Driven Computer Vision
• Low-Power Computer Vision: Status, Challenges, Opportunities
• Guiding the Creation of Deep Learning-based Object Detectors
• Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving
• Grab: Fast and Accurate Sensor Processing for Cashier-Free Shopping
• Deep RNN Framework for Visual Sequential Applications
• NAIS: Neural Architecture and Implementation Search and its Applications in Autonomous Driving
• DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors
• Joint Face Detection and Facial Motion Retargeting for Multiple Faces
• Semantic Feature Matching for Robust Mapping in Agriculture
• REX: Revisiting Budgeted Training with an Improved Schedule
• MuSe 2020 -- The First International Multimodal Sentiment Analysis in Real-life Media Challenge and Workshop
• VASTA: A Vision and Language-assisted Smartphone Task Automation System
• Query by Semantic Sketch
• Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-directional LSTM
• Adversarially Trained Object Detector for Unsupervised Domain Adaptation
• KIT MOMA: A Mobile Machines Dataset
• iffDetector: Inference-aware Feature Filtering for Object Detection
• Rearchitecting Classification Frameworks For Increased Robustness
• Computer Vision-based Social Distancing Surveillance Solution with Optional Automated Camera Calibration for Large Scale Deployment
• DEEPEYE: A Compact and Accurate Video Comprehension at Terminal Devices Compressed with Quantization and Tensorization
• V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection
• Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection
• Report on UG^2+ Challenge Track 1: Assessing Algorithms to Improve Video Object Detection and Classification from Unconstrained Mobility Platforms
• Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
• Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations
• v2e: From Video Frames to Realistic DVS Events
• SaccadeNet: A Fast and Accurate Object Detector
• Improvement of Classification in One-Stage Detector
• Domain Adaptation with Joint Learning for Generic, Optical Car Part Recognition and Detection Systems (Go-CaRD)
• Deep Variational Instance Segmentation
• Single-Stage 6D Object Pose Estimation
• Learning from Videos with Deep Convolutional LSTM Networks
• Applications of Deep Learning in Fundus Images: A Review
• Automatic Generation of Machine Learning Synthetic Data Using ROS
• Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting
• A Compressive Sensing Video dataset using Pixel-wise coded exposure
• OrcVIO: Object residual constrained Visual-Inertial Odometry
• The Challenge of Multi-Operand Adders in CNNs on FPGAs: How not to solve it!
• Detection as Regression: Certified Object Detection by Median Smoothing
• Image-based phenotyping of diverse Rice (Oryza Sativa L.) Genotypes
• Density Map Guided Object Detection in Aerial Images
• Automatic Mapping with Obstacle Identification for Indoor Human Mobility Assessment
• Knowledge Enhanced Neural Fashion Trend Forecasting
• LiDAR Cluster First and Camera Inference Later: A New Perspective Towards Autonomous Driving
• 3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
• RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images
• Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image
• Collage Inference: Using Coded Redundancy for Low Variance Distributed Image Classification
• COMET: Context-Aware IoU-Guided Network for Small Object Tracking
• Enhancing the Association in Multi-Object Tracking via Neighbor Graph
• Integrating NVIDIA Deep Learning Accelerator (NVDLA) with RISC-V SoC on FireSim
• Learning to associate detections for real-time multiple object tracking
• NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination
• Composition and Configuration Patterns in Multiple-View Visualizations
• Locating Cephalometric X-Ray Landmarks with Foveated Pyramid Attention
• Ego-Downward and Ambient Video based Person Location Association
• MMFNet: A Multi-modality MRI Fusion Network for Segmentation of Nasopharyngeal Carcinoma
• Channel-wise Alignment for Adaptive Object Detection
• Multi-Resolution Weak Supervision for Sequential Data
• A Unified Optimization Approach for CNN Model Inference on Integrated GPUs
• Automated Gain Control Through Deep Reinforcement Learning for Downstream Radar Object Detection
• Arc-support Line Segments Revisited: An Efficient and High-quality Ellipse Detection
• Review: deep learning on 3D point clouds
• GLSD: The Global Large-Scale Ship Database and Baseline Evaluations
• Autocamera Calibration for traffic surveillance cameras with wide angle lenses
• Comprehensive and Efficient Data Labeling via Adaptive Model Scheduling
• Mixup Regularization for Region Proposal based Object Detectors
• Long-distance tiny face detection based on enhanced YOLOv3 for unmanned system
• SmartShuttle: Model Based Design and Evaluation of Automated On-Demand Shuttles for Solving the First-Mile and Last-Mile Problem in a Smart City
• Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection
• Sobi: An Interactive Social Service Robot for Long-Term Autonomy in Open Environments
• A Framework for 3D Tracking of Frontal Dynamic Objects in Autonomous Cars
• Multi-Modal Zero-Shot Sign Language Recognition
• Detection Method Based on Automatic Visual Shape Clustering for Pin-Missing Defect in Transmission Lines
• Efficient Pig Counting in Crowds with Keypoints Tracking and Spatial-aware Temporal Response Filtering
• Non-anchor-based vehicle detection for traffic surveillance using bounding ellipses
• An Evaluation of RGB and LiDAR Fusion for Semantic Segmentation
• Shared Mobile-Cloud Inference for Collaborative Intelligence
• Foreground-Background Imbalance Problem in Deep Object Detectors: A Review
• Comparison of object detection methods for crop damage assessment using deep learning
• Self-supervised Robust Object Detectors from Partially Labelled Datasets
• Deeply Activated Salient Region for Instance Search
• KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization
• Learning a Domain Classifier Bank for Unsupervised Adaptive Object Detection
• StampNet: unsupervised multi-class object discovery
• A Dataset and Application for Facial Recognition of Individual Gorillas in Zoo Environments
• DeepSperm: A robust and real-time bull sperm-cell detection in densely populated semen videos
• High-speed object detection with a single-photon time-of-flight image sensor
• TE-YOLOF: Tiny and efficient YOLOF for blood cell detection
• On the Limits to Multi-Modal Popularity Prediction on Instagram -- A New Robust, Efficient and Explainable Baseline
• A New Action Recognition Framework for Video Highlights Summarization in Sporting Events
• A Comprehensive Review on Recent Methods and Challenges of Video Description
• A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation
• Underexposed Image Correction via Hybrid Priors Navigated Deep Propagation
• Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection
• A new way to constrain the densities of intra-group medium in groups of galaxies with convolutional neural networks
• Vision based Target Interception using Aerial Manipulation
• Improving Traffic Safety Through Video Analysis in Jakarta, Indonesia
• Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps
• SNIDER: Single Noisy Image Denoising and Rectification for Improving License Plate Recognition
• Towards Adversarially Robust Object Detection
• Airplane Detection Based on Mask Region Convolution Neural Network
• Boosting Image Outpainting with Semantic Layout Prediction
• Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019
• Semantic SLAM with Autonomous Object-Level Data Association
• Egoshots, an ego-vision life-logging dataset and semantic fidelity metric to evaluate diversity in image captioning models
• FRDet: Balanced and Lightweight Object Detector based on Fire-Residual Modules for Embedded Processor of Autonomous Driving
• Toward Autonomous Rotation-Aware Unmanned Aerial Grasping
• Learning to Navigate from Simulation via Spatial and Semantic Information Synthesis with Noise Model Embedding
• Object grasping planning for the situation when soft and rigid objects are mixed together
• AFD-Net: Adaptive Fully-Dual Network for Few-Shot Object Detection
• Object-aware Feature Aggregation for Video Object Detection
• Improving the Transferability of Adversarial Examples with New Iteration Framework and Input Dropout
• VGAI: End-to-End Learning of Vision-Based Decentralized Controllers for Robot Swarms
• Chargrid-OCR: End-to-end Trainable Optical Character Recognition for Printed Documents using Instance Segmentation
• Multiple Object Tracking with Motion and Appearance Cues
• Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
• DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks
• Resource-Constrained Simultaneous Detection and Labeling of Objects in High-Resolution Satellite Images
• One-Shot Imitation Filming of Human Motion Videos
• Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones
• Pavement Distress Detection and Segmentation using YOLOv4 and DeepLabv3 on Pavements in the Philippines
• Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes
• Compact 3D Map-Based Monocular Localization Using Semantic Edge Alignment
• PPGN: Phrase-Guided Proposal Generation Network For Referring Expression Comprehension
• Putting visual object recognition in context
• X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments
• Class-Aware Robust Adversarial Training for Object Detection
• Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators
• Towards Improving Spatiotemporal Action Recognition in Videos
• Multiple Object Tracking with Correlation Learning
• Open data for Moroccan license plates for OCR applications : data collection, labeling, and model construction
• A Unified Framework of Constrained Robust Submodular Optimization with Applications
• Exploring 2D Data Augmentation for 3D Monocular Object Detection
• PREGAN: Pose Randomization and Estimation for Weakly Paired Image Style Translation
• When We First Met: Visual-Inertial Person Localization for Co-Robot Rendezvous
• Red Blood Cell Segmentation with Overlapping Cell Separation and Classification on Imbalanced Dataset
• Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs
• An Efficient UAV-based Artificial Intelligence Framework for Real-Time Visual Tasks
• Towards Better Object Detection in Scale Variation with Adaptive Feature Selection
• Robustness Enhancement of Object Detection in Advanced Driver Assistance Systems (ADAS)
• DetectFusion: Detecting and Segmenting Both Known and Unknown Dynamic Objects in Real-time SLAM
• TYolov5: A Temporal Yolov5 Detector Based on Quasi-Recurrent Neural Networks for Real-Time Handgun Detection in Video
• Meta Adversarial Training against Universal Patches
• LeagueAI: Improving object detector performance and flexibility through automatically generated training data and domain randomization
• INSTA-YOLO: Real-Time Instance Segmentation
• Image-based monitoring of bolt loosening through deep-learning-based integrated detection and tracking
• Developing a Compressed Object Detection Model based on YOLOv4 for Deployment on Embedded GPU Platform of Autonomous System
• Mining Deep And-Or Object Structures via Cost-Sensitive Question-Answer-Based Active Annotations
• Semi-supervised Breast Lesion Detection in Ultrasound Video Based on Temporal Coherence
• Vision-based Pedestrian Alert Safety System (PASS) for Signalized Intersections
• YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving
• A Novel and Efficient Tumor Detection Framework for Pancreatic Cancer via CT Images
• Real-Time target detection in maritime scenarios based on YOLOv3 model
• Depth Based Semantic Scene Completion with Position Importance Aware Loss
• Robotic Grasp Manipulation Using Evolutionary Computing and Deep Reinforcement Learning
• A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
• Vision: A Deep Learning Approach to provide walking assistance to the visually impaired
• Language-guided Semantic Mapping and Mobile Manipulation in Partially Observable Environments
• Practical License Plate Recognition in Unconstrained Surveillance Systems with Adversarial Super-Resolution
• Few-shot Object Detection with Self-adaptive Attention Network for Remote Sensing Images
• Performance of object recognition in wearable videos
• GPR-based Subsurface Object Detection and Reconstruction Using Random Motion and DepthNet
• CCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection
• A Smartphone-based System for Real-time Early Childhood Caries Diagnosis
• Deep Learning-based Human Detection for UAVs with Optical and Infrared Cameras: System and Experiments
• U2-ONet: A Two-level Nested Octave U-structure with Multiscale Attention Mechanism for Moving Instances Segmentation
• Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry
• A Survey on Sensor Technologies for Unmanned Ground Vehicles
• Understanding Object Detection Through An Adversarial Lens
• EDSL: An Encoder-Decoder Architecture with Symbol-Level Features for Printed Mathematical Expression Recognition
• Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection
• Expandable YOLO: 3D Object Detection from RGB-D Images
• Seismic Shot Gather Noise Localization Using a Multi-Scale Feature-Fusion-Based Neural Network
• Probabilistic Oriented Object Detection in Automotive Radar
• Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection
• Improved YOLOv3 Object Classification in Intelligent Transportation System
• Rapid Detection of Aircrafts in Satellite Imagery based on Deep Neural Networks
• Application of Computer Vision and Machine Learning for Digitized Herbarium Specimens: A Systematic Literature Review
• Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks
• Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning
• Serial-parallel Multi-Scale Feature Fusion for Anatomy-Oriented Hand Joint Detection
• PatternMonitor: a whole pipeline with a much higher level of automation for guessing Android lock pattern based on videos
• Domain Adaptive Object Detection via Feature Separation and Alignment
• Movement Tracks for the Automatic Detection of Fish Behavior in Videos
• Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos
• End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining
• DPNET: Dual-Path Network for Efficient Object Detectioj with Lightweight Self-Attention
• Comparison of Object Detection Algorithms Using Video and Thermal Images Collected from a UAS Platform: An Application of Drones in Traffic Management
• Cell Detection from Imperfect Annotation by Pseudo Label Selection Using P-classification
• Residual Error: a New Performance Measure for Adversarial Robustness
• Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks
• The MIS Check-Dam Dataset for Object Detection and Instance Segmentation Tasks
• Detection of E-scooter Riders in Naturalistic Scenes
• A Survey of Fish Tracking Techniques Based on Computer Vision
• Gated recurrent units and temporal convolutional network for multilabel classification
• A Better Loss for Visual-Textual Grounding
• Humans as Path-Finders for Safe Navigation
• Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
• A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection
• Object Localization Through a Single Multiple-Model Convolutional Neural Network with a Specific Training Approach
• Confidence Calibration with Bounded Error Using Transformations
• More Reliable AI Solution: Breast Ultrasound Diagnosis Using Multi-AI Combination
• Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning
• Behavioural pattern discovery from collections of egocentric photo-streams
• Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos
• 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?
• LAMP: Large-Scale Autonomous Mapping and Positioning for Exploration of Perceptually-Degraded Subterranean Environments
• Real-Time Panoptic Segmentation from Dense Detections
• Grounding-Tracking-Integration
• Deep Mixture Density Network for Probabilistic Object Detection
• STA: Adversarial Attacks on Siamese Trackers
• From perception to control: an autonomous driving system for a formula student driverless car
• Scraping Social Media Photos Posted in Kenya and Elsewhere to Detect and Analyze Food Types
• An Objectness Score for Accurate and Fast Detection during Navigation
• Feedbackward Decoding for Semantic Segmentation
• Dynamic Region Division for Adaptive Learning Pedestrian Counting
• Instance Scale Normalization for image understanding
• Reprojection R-CNN: A Fast and Accurate Object Detector for 360° Images
• Interpretable Neural Network Decoupling
• QANet -- Quality Assurance Network for Image Segmentation
• Training Quantized Neural Networks with a Full-precision Auxiliary Module
• FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds
• Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images
• FotonNet: A HW-Efficient Object Detection System Using 3D-Depth Segmentation and 2D-DNN Classifier
• Intelligent flat-and-textureless object manipulation in Service Robots
• Object Detection from Scratch with Deep Supervision
• Multi-object Tracking with Tracked Object Bounding Box Association
• Understanding Video Content: Efficient Hero Detection and Recognition for the Game "Honor of Kings"
• Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration
• A Bioinspired Retinal Neural Network for Accurately Extracting Small-Target Motion Information in Cluttered Backgrounds
• ST-DETR: Spatio-Temporal Object Traces Attention Detection Transformer
• Testbed for Connected Artificial Intelligence using Unmanned Aerial Vehicles and Convolutional Pose Machines
• Inserting Videos into Videos
• Autonomous detection of molecular configurations in microscopic images based on deep convolutional neural network
• An Experience Report on Machine Learning Reproducibility: Guidance for Practitioners and TensorFlow Model Garden Contributors
• Boosting ship detection in SAR images with complementary pretraining techniques
• Live Reconstruction of Large-Scale Dynamic Outdoor Worlds
• Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos
• Learning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images
• Abnormal Behavior Detection Based on Target Analysis
• Technical Report: Reactive Semantic Planning in Unexplored Semantic Environments Using Deep Perceptual Feedback
• Semantic Segmentation and Object Detection Towards Instance Segmentation: Breast Tumor Identification
• ShortcutFusion: From Tensorflow to FPGA-based accelerator with reuse-aware memory allocation for shortcut data
• Strawberry Detection Using a Heterogeneous Multi-Processor Platform
• On Applying Machine Learning/Object Detection Models for Analysing Digitally Captured Physical Prototypes from Engineering Design Projects
• Pedestrian Detection in 3D Point Clouds using Deep Neural Networks
• Enabling Incremental Knowledge Transfer for Object Detection at the Edge
• Camera Exposure Control for Robust Robot Vision with Noise-Aware Image Quality Assessment
• SurveilEdge: Real-time Video Query based on Collaborative Cloud-Edge Deep Learning
• An Inter-Layer Weight Prediction and Quantization for Deep Neural Networks based on a Smoothly Varying Weight Hypothesis
• ZS-SLR: Zero-Shot Sign Language Recognition from RGB-D Videos
• On Designing Computing Systems for Autonomous Vehicles: a PerceptIn Case Study
• Small Object Detection Based on Modified FSSD and Model Compression
• What is the appropriate speed for an autonomous vehicle? Designing a Pedestrian Aware Contextual Speed Controller
• A Cost Effective Solution for Road Crack Inspection using Cameras and Deep Neural Networks
• Defocus Blur Detection via Salient Region Detection Prior
• Deep Knowledge Tracing with Learning Curves
• RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
• Deployment of Customized Deep Learning based Video Analytics On Surveillance Cameras
• Fashion-Guided Adversarial Attack on Person Segmentation
• Detecting and Matching Related Objects with One Proposal Multiple Predictions
• Energy Drain of the Object Detection Processing Pipeline for Mobile Devices: Analysis and Implications
• Video Anomaly Detection by Estimating Likelihood of Representations
• Variational Pedestrian Detection
• Cascading Neural Network Methodology for Artificial Intelligence-Assisted Radiographic Detection and Classification of Lead-Less Implanted Electronic Devices within the Chest
• Semantic Segmentation for Compound figures
• Learning Universal Shape Dictionary for Realtime Instance Segmentation
• Deep Learning Based FDD Non-Stationary Massive MIMO Downlink Channel Reconstruction
• Let Your Camera See for You: A Novel Two-Factor Authentication Method against Real-Time Phishing Attacks
• Mask R-CNN Based Object Detection for Intelligent Wireless Power Transfer
• Table understanding in structured documents
• Natural Adversarial Objects
• SafeAccess+: An Intelligent System to make Smart Home Safer and Americans with Disability Act Compliant
• Global Context Aware RCNN for Object Detection
• Scope Head for Accurate Localization in Object Detection
• Towards Class-incremental Object Detection with Nearest Mean of Exemplars
• Expedited Multi-Target Search with Guaranteed Performance via Multi-fidelity Gaussian Processes
• NENET: An Edge Learnable Network for Link Prediction in Scene Text
• Learning to adapt class-specific features across domains for semantic segmentation
• Multiple Myeloma Cancer Cell Instance Segmentation
• You Cannot Easily Catch Me: A Low-Detectable Adversarial Patch for Object Detectors
• Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks
• Residual Squeeze-and-Excitation Network for Fast Image Deraining
• MSDU-net: A Multi-Scale Dilated U-net for Blur Detection
• An improved helmet detection method for YOLOv3 on an unbalanced dataset
• Convolutional neural networks compression with low rank and sparse tensor decompositions
• Ink removal from histopathology whole slide images by combining classification, detection and image generation models
• Pixel Invisibility: Detecting Objects Invisible in Color Images
• Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection
• Classifying logistic vehicles in cities using Deep learning
• Towards in-store multi-person tracking using head detection and track heatmaps
• N 2 C : Neural Network Controller Design Using Behavioral Cloning
• Pose2RGBD. Generating Depth and RGB images from absolute positions
• Dive Deeper Into Box for Object Detection
• DeepTEGINN: Deep Learning Based Tools to Extract Graphs from Images of Neural Networks
• Deep Learning Based Traffic Surveillance System For Missing and Suspicious Car Detection
• Inter-Homines: Distance-Based Risk Estimation for Human Safety
• A Study on Evaluation Standard for Automatic Crack Detection Regard the Random Fractal
• Weakly supervised one-stage vision and language disease detection using large scale pneumonia and pneumothorax studies
• Strawberry Detection using Mixed Training on Simulated and Real Data
• Spatiotemporal Action Recognition in Restaurant Videos
• ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search
• Exploring Effectiveness of Inter-Microtask Qualification Tests in Crowdsourcing
• Computation and Communication Co-Design for Real-Time Monitoring and Control in Multi-Agent Systems
• Accurate and Robust Object-oriented SLAM with 3D Quadric Landmark Construction in Outdoor Environment
• An Artificial Intelligence System for Combined Fruit Detection and Georeferencing, Using RTK-Based Perspective Projection in Drone Imagery
• PTQ-SL: Exploring the Sub-layerwise Post-training Quantization
• Towards Automated Swimming Analytics Using Deep Neural Networks
• PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation
• Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection
• WDR FACE: The First Database for Studying Face Detection in Wide Dynamic Range
• Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales
• QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM
• Inverting and Understanding Object Detectors
• Target Reaching Behaviour for Unfreezing the Robot in a Semi-Static and Crowded Environment
• IMMVP: An Efficient Daytime and Nighttime On-Road Object Detector
• Congestion Analysis of Convolutional Neural Network-Based Pedestrian Counting Methods on Helicopter Footage
• Substitute Teacher Networks: Learning with Almost No Supervision
• Latent-Space Inpainting for Packet Loss Concealment in Collaborative Object Detection
• The distance between the weights of the neural network is meaningful
• DeepACEv2: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks
• Pyramid Vector Quantization and Bit Level Sparsity in Weights for Efficient Neural Networks Inference
• DeepGoal: Learning to Drive with driving intention from Human Control Demonstration
• Meaning guided video captioning
• DeepCore: Convolutional Neural Network for high $p_T$ jet tracking
• DAF-NET: a saliency based weakly supervised method of dual attention fusion for fine-grained image classification
• Robust, Extensible, and Fast: Teamed Classifiers for Vehicle Tracking and Vehicle Re-ID in Multi-Camera Networks
• PointINS: Point-based Instance Segmentation
• UMLE: Unsupervised Multi-discriminator Network for Low Light Enhancement
• Reactive Human-to-Robot Handovers of Arbitrary Objects
• MLMA-Net: multi-level multi-attentional learning for multi-label object detection in textile defect images
• Top-K Deep Video Analytics: A Probabilistic Approach
• RTGPU: Real-Time GPU Scheduling of Hard Deadline Parallel Tasks with Fine-Grain Utilization
• R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving
• Efficient Pedestrian Detection in Top-View Fisheye Images Using Compositions of Perspective View Patches
• Real-time Human-Robot Collaborative Manipulations of Cylindrical and Cubic Objects via Geometric Primitives and Depth Information
• Machine Learning Techniques to Detect and Characterise Whistler Radio Waves
• TLGAN: document Text Localization using Generative Adversarial Nets
• Deep Sensing of Urban Waterlogging
• Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection
• Real-Time Dense Mapping for Self-driving Vehicles using Fisheye Cameras
• Deep Submodular Networks for Extractive Data Summarization
• Privacy Aware Person Detection in Surveillance Data
• SOLO: A Simple Framework for Instance Segmentation
• Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity
• The Amazing Race TM: Robot Edition
• Self-Reorganizing and Rejuvenating CNNs for Increasing Model Capacity Utilization
• Financial ticket intelligent recognition system based on deep learning
• MFPP: Morphological Fragmental Perturbation Pyramid for Black-Box Model Explanations
• Adaptation and Generalization for Unknown Sensitive Factors of Variations
• Multi-frame Collaboration for Effective Endoscopic Video Polyp Detection via Spatial-Temporal Feature Transformation
• Histogram of Cell Types: Deep Learning for Automated Bone Marrow Cytology
• Understanding Uncertainty of Edge Computing: New Principle and Design Approach
• D-VPnet: A Network for Real-time Dominant Vanishing Point Detection in Natural Scenes
• Learning and Reasoning with the Graph Structure Representation in Robotic Surgery
• Robust Learning with Frequency Domain Regularization
• Object Detection-Based Variable Quantization Processing
• 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
• A Deep Learning-Based Autonomous RobotManipulator for Sorting Application
• Interpretation of smartphone-captured radiographs utilizing a deep learning-based approach
• CSI2Image: Image Reconstruction from Channel State Information Using Generative Adversarial Networks
• CoFF: Cooperative Spatial Feature Fusion for 3D Object Detection on Autonomous Vehicles
• BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model
• Non-local RoI for Cross-Object Perception
• Did you miss it? Automatic lung nodule detection combined with gaze information improves radiologists' screening performance
• Background Segmentation for Vehicle Re-Identification
• Proactive Network Maintenance using Fast, Accurate Anomaly Localization and Classification on 1-D Data Series
• Pano: Optimizing 360° Video Streaming with a Better Understanding of Quality Perception
• Model Adaption Object Detection System for Robot
• Teaching Perception
• Large-scale Multi-modal Person Identification in Real Unconstrained Environments
• Zero Cost Improvements for General Object Detection Network
• Channel Boosting Feature Ensemble for Radar-based Object Detection
• Semi-Automatic Annotation For Visual Object Tracking
• QuickBrowser: A Unified Model to Detect and Read Simple Object in Real-time
• The Detection of Thoracic Abnormalities ChestX-Det10 Challenge Results
• OSKDet: Towards Orientation-sensitive Keypoint Localization for Rotated Object Detection
• Efficient Online Transfer Learning for 3D Object Classification in Autonomous Driving
• Robotic Waste Sorter with Agile Manipulation and Quickly Trainable Detector
• Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection
• Automatic Visual Inspection of Rare Defects: A Framework based on GP-WGAN and Enhanced Faster R-CNN
• Towards an efficient framework for Data Extraction from Chart Images
• A Study on Trees's Knots Prediction from their Bark Outer-Shape
• A Comparative Study on Effects of Original and Pseudo Labels for Weakly Supervised Learning for Car Localization Problem
• Video Surveillance for Road Traffic Monitoring
• Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment
• TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video
• Distilling Image Classifiers in Object Detectors
• Auto-calibration Method Using Stop Signs for Urban Autonomous Driving Applications
• Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs
• Bridging the Gap Between Object Detection and User Intent via Query-Modulation
• BNAS-v2: Memory-efficient and Performance-collapse-prevented Broad Neural Architecture Search
• ISyNet: Convolutional Neural Networks design for AI accelerator
• NarrationBot and InfoBot: A Hybrid System for Automated Video Description
• How Well Do Sparse Imagenet Models Transfer?
• Boundary Distribution Estimation for Precise Object Detection
• NoFADE: Analyzing Diminishing Returns on CO2 Investment
• MIXER: A Principled Framework for Multimodal, Multiway Data Association
• ePose: Let's Make EfficientPose More Generally Applicable
• Semi-Supervised Surface Anomaly Detection of Composite Wind Turbine Blades From Drone Imagery
• Non-local RoIs for Instance Segmentation
• Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation
• AGSFCOS: Based on attention mechanism and Scale-Equalizing pyramid network of object detection
• Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
• ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass
• Development of a conversing and body temperature scanning autonomously navigating robot to help screen for COVID-19
• Synthetic-to-Real Domain Adaptation for Lane Detection
• Dynamic Error-bounded Lossy Compression (EBLC) to Reduce the Bandwidth Requirement for Real-time Vision-based Pedestrian Safety Applications
• Attention-based Neural Network for Driving Environment Complexity Perception
• Obstacle Detection for BVLOS Drones
• SIMPL: Generating Synthetic Overhead Imagery to Address Zero-shot and Few-Shot Detection Problems
• Empowering cyberphysical systems of systems with intelligence
• Towards Robustness against Unsuspicious Adversarial Examples
• Angel's Girl for Blind Painters: an Efficient Painting Navigation System Validated by Multimodal Evaluation Approach
• ARDOP: A Versatile Humanoid Robotic Research Platform
• DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data
• Enlisting 3D Crop Models and GANs for More Data Efficient and Generalizable Fruit Detection
• Autonomous Cooperative Multi-Vehicle System for Interception of Aerial and Stationary Targets in Unknown Environments
• EOLO: Embedded Object Segmentation only Look Once
• Multi-Scale Aligned Distillation for Low-Resolution Detection
• Humanly Certifying Superhuman Classifiers
• Simultaneous Learning from Human Pose and Object Cues for Real-Time Activity Recognition
• Adversarial Semantic Contour for Object Detection
• Deep Learning Approach Protecting Privacy in Camera-Based Critical Applications
• Talking Detection In Collaborative Learning Environments
• Towards Toxic and Narcotic Medication Detection with Rotated Object Detector
• Measurement-driven Analysis of an Edge-Assisted Object Recognition System
• RODNet: Radar Object Detection Using Cross-Modal Supervision
• NAS-FCOS: Efficient Search for Object Detection Architectures
• Generative Residual Attention Network for Disease Detection
• Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network
• OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement
• Video based real-time positional tracker
• "Who is Driving around Me?" Unique Vehicle Instance Classification using Deep Neural Features
• Ink Marker Segmentation in Histopathology Images Using Deep Learning
• L6DNet: Light 6 DoF Network for Robust and Precise Object Pose Estimation with Small Datasets
• Efficient Pipelines for Vision-Based Context Sensing
• DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection
• Two-stage multi-scale breast mass segmentation for full mammogram analysis without user intervention
• Does Thermal data make the detection systems more reliable?
• Defense-guided Transferable Adversarial Attacks
• Fast Object Detection with Latticed Multi-Scale Feature Fusion
• Weighted Average Precision: Adversarial Example Detection in the Visual Perception of Autonomous Vehicles
• Multi-regime analysis for computer vision-based traffic surveillance using a change-point detection algorithm
• Faster object tracking pipeline for real time tracking
• Pixel-Semantic Revise of Position Learning A One-Stage Object Detector with A Shared Encoder-Decoder
• Weakly Supervised Instance Segmentation by Deep Community Learning
• FPAENet: Pneumonia Detection Network Based on Feature Pyramid Attention Enhancement
• Attentional-GCNN: Adaptive Pedestrian Trajectory Prediction towards Generic Autonomous Vehicle Use Cases
• Real-Time Object Detection and Localization in Compressive Sensed Video on Embedded Hardware
• Enabling Collaborative Video Sensing at the Edge through Convolutional Sharing
• Sim-to-Real Transfer of Robot Learning with Variable Length Inputs
• ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture
• Skeleon-Based Typing Style Learning For Person Identification
• R-AGNO-RPN: A LIDAR-Camera Region Deep Network for Resolution-Agnostic Detection
• A MAC-less Neural Inference Processor Supporting Compressed, Variable Precision Weights
• Robust Real-Time Pedestrian Detection on Embedded Devices
• Application of the Neural Network Dependability Kit in Real-World Environments
• Decoupled Self Attention for Accurate One Stage Object Detection
• LiveMap: Real-Time Dynamic Map in Automotive Edge Computing
• Dense Multiscale Feature Fusion Pyramid Networks for Object Detection in UAV-Captured Images
• Trained Model Fusion for Object Detection using Gating Network
• 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
• Dynamic DNN Decomposition for Lossless Synergistic Inference
• Large-scale Gastric Cancer Screening and Localization Using Multi-task Deep Neural Network
• A Unified Light Framework for Real-time Fault Detection of Freight Train Images
• Compressed Object Detection
• Assembly of randomly placed parts realized by using only one robot arm with a general parallel-jaw gripper
• Custom Object Detection via Multi-Camera Self-Supervised Learning
• Mining Minimal Map-Segments for Visual Place Classifiers
• Turkey Behavior Identification System with a GUI Using Deep Learning and Video Analytics
• HishabNet: Detection, Localization and Calculation of Handwritten Bengali Mathematical Expressions
• RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection
• A Generic Object Re-identification System for Short Videos
• Universal Physical Camouflage Attacks on Object Detectors
• Phase Space Reconstruction Network for Lane Intrusion Action Recognition
• Probabilistic Spatial Analysis in Quantitative Microscopy with Uncertainty-Aware Cell Detection using Deep Bayesian Regression of Density Maps
• An Adaptive Video Acquisition Scheme for Object Tracking and its Performance Optimization
• Auto-Detection of Tibial Plateau Angle in Canine Radiographs Using a Deep Learning Approach
• A Mobile Robot Generating Video Summaries of Seniors' Indoor Activities
• Can We Automate Diagrammatic Reasoning?
• A Practical Framework for ROI Detection in Medical Images -- a case study for hip detection in anteroposterior pelvic radiographs
• LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment
• Robust 2D/3D Vehicle Parsing in CVIS
• TagMe: GPS-Assisted Automatic Object Annotation in Videos
• Estimation of Closest In-Path Vehicle (CIPV) by Low-Channel LiDAR and Camera Sensor Fusion for Autonomous Vehicle
• Relation-Aware Pyramid Network (RapNet) for temporal action proposal
• Maximum Lifetime Analytics in IoT Networks
• Modulating Localization and Classification for Harmonized Object Detection
• MultiScope: Efficient Video Pre-processing for Exploratory Video Analytics
• Multi-directional Bicycle Robot for Steel Structure Inspection
• Knowledge Distillation By Sparse Representation Matching
• Wide-Depth-Range 6D Object Pose Estimation in Space
• Using Python for Model Inference in Deep Learning
• Research on Optimization Method of Multi-scale Fish Target Fast Detection Network
• Detection of Dataset Shifts in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
• AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks
• GuideBP: Guiding Backpropagation Through Weaker Pathways of Parallel Logits
• Semantics to Space(S2S): Embedding semantics into spatial space for zero-shot verb-object query inferencing
• Empirical Upper Bound, Error Diagnosis and Invariance Analysis of Modern Object Detectors
• Convolutional Neural Networks for Real-Time Localization and Classification in Feedback Digital Microscopy
• Multimodal and multiview distillation for real-time player detection on a football field
• FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange
• Complex-Object Visual Inspection via Multiple Lighting Configurations
• Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios
• Leveraging Orientation for Weakly Supervised Object Detection with Application to Firearm Localization
• Joint-SRVDNet: Joint Super Resolution and Vehicle Detection Network
• Anchors Based Method for Fingertips Position Estimation from a Monocular RGB Image using Deep Neural Network
• Object Detection in Specific Traffic Scenes using YOLOv2
• Adversarial Robustness of Deep Convolutional Candlestick Learner
• Implementing AI-powered semantic character recognition in motor racing sports