Recurrent Models of Visual Attention

Abstract

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution. Like convolutional neural networks, the proposed model has a degree of translation invariance built-in, but the amount of computation it performs can be controlled independently of the input image size. While the model is non-differentiable, it can be trained using reinforcement learning methods to learn task-specific policies. We evaluate our model on several image classification tasks, where it significantly outperforms a convolutional neural network baseline on cluttered images, and on a dynamic visual control problem, where it learns to track a simple object without an explicit training signal for doing so.

References in corpus (1)

• On Learning Where To Look

Cited by in corpus (380)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• A Survey on Visual Transformer
• Teaching Machines to Read and Comprehend
• Attention Mechanisms in Computer Vision: A Survey
• Attention-Based Models for Speech Recognition
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Sequence Level Training with Recurrent Neural Networks
• Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning
• Deep neural network models for computational histopathology: A survey
• Effective Approaches to Attention-based Neural Machine Translation
• Attention in Natural Language Processing
• Reasoning about Entailment with Neural Attention
• Deep Reinforcement Learning: An Overview
• Wireless Image Transmission Using Deep Source Channel Coding With Attention Modules
• Action Recognition using Visual Attention
• CBAM: Convolutional Block Attention Module
• Coordinate Attention for Efficient Mobile Network Design
• A Comprehensive Survey of Scene Graphs: Generation and Application
• Residual Attention Network for Image Classification
• Learning Attentional Communication for Multi-Agent Cooperation
• Actor-Attention-Critic for Multi-Agent Reinforcement Learning
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• Concept Whitening for Interpretable Image Recognition
• ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
• Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach
• Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis
• Microstructural Materials Design via Deep Adversarial Learning Methodology
• Image Captioning with Semantic Attention
• Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
• SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting
• Object-Centric Learning with Slot Attention
• Discovering Discrete Latent Topics with Neural Variational Inference
• Attention-based Convolutional Neural Network for Weakly Labeled Human Activities Recognition with Wearable Sensors
• Natural Language Processing Advancements By Deep Learning: A Survey
• Attention Enriched Deep Learning Model for Breast Tumor Segmentation in Ultrasound Images
• RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification
• Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record
• Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
• Gradient Estimation Using Stochastic Computation Graphs
• Graph Neural Networks: Taxonomy, Advances and Trends
• Artificial Neural Network with Physical Dynamic Metasurface Layer for Optimal Sensing
• Conditional Computation in Neural Networks for faster models
• Variational inference for Monte Carlo objectives
• Foveation-based Mechanisms Alleviate Adversarial Examples
• Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition
• A Convolutional Attention Network for Extreme Summarization of Source Code
• Learn to Combine Modalities in Multimodal Deep Learning
• Learning to detect chest radiographs containing lung nodules using visual attention networks
• Fully Convolutional Attention Networks for Fine-Grained Recognition
• Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
• BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
• Learn To Pay Attention
• Recurrent Mixture Density Network for Spatiotemporal Visual Attention
• PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions
• Full-Capacity Unitary Recurrent Neural Networks
• Streaming convolutional neural networks for end-to-end learning with multi-megapixel images
• Reinforcement Learning Neural Turing Machines - Revised
• Review: Deep Learning in Electron Microscopy
• Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
• OpenSpiel: A Framework for Reinforcement Learning in Games
• Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks
• Deep Reinforcement Learning for Visual Object Tracking in Videos
• Survey on the attention based RNN model and its applications in computer vision
• Hierarchical Paired Channel Fusion Network for Street Scene Change Detection
• Deep Attention Recurrent Q-Network
• DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks
• Intelligent Meta-Imagers: From Compressed to Learned Sensing
• Too Far to See? Not Really! --- Pedestrian Detection with Scale-aware Localization Policy
• Learning a Discriminative Feature Network for Semantic Segmentation
• Tree-Structured Reinforcement Learning for Sequential Object Localization
• Neural Models for Information Retrieval
• Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
• Neural Reverse Engineering of Stripped Binaries using Augmented Control Flow Graphs
• Attentive Recurrent Comparators
• Active Learning in Robotics: A Review of Control Principles
• One-Shot Generalization in Deep Generative Models
• Attention Correctness in Neural Image Captioning
• Pose-conditioned Spatio-Temporal Attention for Human Action Recognition
• A Survey of Automatic Generation of Source Code Comments: Algorithms and Techniques
• Attention-guided Context Feature Pyramid Network for Object Detection
• Neural Speed Reading via Skim-RNN
• Cloud Removal for Remote Sensing Imagery via Spatial Attention Generative Adversarial Network
• Bilinear CNNs for Fine-grained Visual Recognition
• Infrared and 3D skeleton feature fusion for RGB-D action recognition
• PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
• Visual Attention Network for Low Dose CT
• MGP-AttTCN: An Interpretable Machine Learning Model for the Prediction of Sepsis
• DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
• ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs
• Attentive Generative Adversarial Network for Raindrop Removal from a Single Image
• Is Attention Better Than Matrix Decomposition?
• First Step toward Model-Free, Anonymous Object Tracking with Recurrent Neural Networks
• Recurrent Attentional Networks for Saliency Detection
• On the Binding Problem in Artificial Neural Networks
• Video Storytelling: Textual Summaries for Events
• Droidetec: Android Malware Detection and Malicious Code Localization through Deep Learning
• Wavelet Channel Attention Module with a Fusion Network for Single Image Deraining
• Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification
• Multi-Task Representation Learning with Multi-View Graph Convolutional Networks
• Generating Text with Deep Reinforcement Learning
• Channel Distillation: Channel-Wise Attention for Knowledge Distillation
• Dynamic Neural Networks: A Survey
• SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
• Implicit Distortion and Fertility Models for Attention-based Encoder-Decoder NMT Model
• End-to-end Learning of Action Detection from Frame Glimpses in Videos
• Recurrent Spatial Transformer Networks
• An empirical study on the effectiveness of images in Multimodal Neural Machine Translation
• Saccader: Improving Accuracy of Hard Attention Models for Vision
• Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
• Beyond Visual Semantics: Exploring the Role of Scene Text in Image Understanding
• Learning from Few Samples: A Survey
• PatchNet: Hierarchical Deep Learning-Based Stable Patch Identification for the Linux Kernel
• NASNet: A Neuron Attention Stage-by-Stage Net for Single Image Deraining
• Meta-Gradient Reinforcement Learning with an Objective Discovered Online
• 3G structure for image caption generation
• Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning
• Multimodal Unified Attention Networks for Vision-and-Language Interactions
• Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
• Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention
• Detecting Statistical Interactions from Neural Network Weights
• It Takes Two to Tango: Towards Theory of AI's Mind
• UntrimmedNets for Weakly Supervised Action Recognition and Detection
• Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning
• Learning to Compose Dynamic Tree Structures for Visual Contexts
• GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud
• MuProp: Unbiased Backpropagation for Stochastic Neural Networks
• Show, Attend and Interact: Perceivable Human-Robot Social Interaction through Neural Attention Q-Network
• Pose is all you need: The pose only group activity recognition system (POGARS)
• Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
• Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition
• rnn : Recurrent Library for Torch
• Transcribing Content from Structural Images with Spotlight Mechanism
• Less Is More: Picking Informative Frames for Video Captioning
• Towards Interpretable Reinforcement Learning Using Attention Augmented Agents
• Higher-order Graph Convolutional Networks
• Audio Visual Emotion Recognition with Temporal Alignment and Perception Attention
• Spatially Adaptive Computation Time for Residual Networks
• Improving Neural Relation Extraction with Implicit Mutual Relations
• Learning 6-DoF Grasping and Pick-Place Using Attention Focus
• Learning efficient haptic shape exploration with a rigid tactile sensor array
• Binding via Reconstruction Clustering
• Emergence of foveal image sampling from learning to attend in visual scenes
• Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding
• Textual Entailment with Structured Attentions and Composition
• Attention-based Ensemble for Deep Metric Learning
• Towards causal generative scene models via competition of experts
• Deep Learning in Bioinformatics
• Self-Attention Capsule Networks for Object Classification
• Multi-Agent Game Abstraction via Graph Attention Neural Network
• Learning Wake-Sleep Recurrent Attention Models
• Sequential Context Encoding for Duplicate Removal
• Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
• Learning Individually Inferred Communication for Multi-Agent Cooperation
• Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendation
• MERANet: Facial Micro-Expression Recognition using 3D Residual Attention Network
• Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition
• Learning to decompose for object detection and instance segmentation
• Joint Iris Segmentation and Localization Using Deep Multi-task Learning Framework
• Dynamic Computational Time for Visual Attention
• AUNet: Attention-guided dense-upsampling networks for breast mass segmentation in whole mammograms
• Recurrent Attention Unit
• Fine-Grained Age Estimation in the wild with Attention LSTM Networks
• Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition
• Learning Blended, Precise Semantic Program Embeddings
• Neural Discourse Relation Recognition with Semantic Memory
• The Benefit of Distraction: Denoising Remote Vitals Measurements using Inverse Attention
• A scalable saliency-based Feature selection method with instance level information
• AdaFrame: Adaptive Frame Selection for Fast Video Recognition
• Guided Zoom: Questioning Network Evidence for Fine-grained Classification
• CATA++: A Collaborative Dual Attentive Autoencoder Method for Recommending Scientific Articles
• Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Execution
• AMC: Attention guided Multi-modal Correlation Learning for Image Search
• Real-time 3D Deep Multi-Camera Tracking
• A Perspective on Objects and Systematic Generalization in Model-Based RL
• Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset
• PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
• Human Attention in Fine-grained Classification
• Learning to Generate with Memory
• Understanding More about Human and Machine Attention in Deep Neural Networks
• A Spatially and Temporally Attentive Joint Trajectory Prediction Framework for Modeling Vessel Intent
• Speech-Based Visual Question Answering
• Folksonomication: Predicting Tags for Movies from Plot Synopses Using Emotion Flow Encoded Neural Network
• Motion Prediction Under Multimodality with Conditional Stochastic Networks
• Pack and Detect: Fast Object Detection in Videos Using Region-of-Interest Packing
• An initial attempt of combining visual selective attention with deep reinforcement learning
• Visual Saliency Maps Can Apply to Facial Expression Recognition
• Knowledge Squeezed Adversarial Network Compression
• Indices Matter: Learning to Index for Deep Image Matting
• Active Perception using Light Curtains for Autonomous Driving
• Image-embodied Knowledge Representation Learning
• The Value Equivalence Principle for Model-Based Reinforcement Learning
• Reversible Recursive Instance-level Object Segmentation
• Abstractive Text Classification Using Sequence-to-convolution Neural Networks
• In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processes
• StartNet: Online Detection of Action Start in Untrimmed Videos
• A Hierarchical Contextual Attention-based GRU Network for Sequential Recommendation
• Hyperspectral Image Classification with Attention Aided CNNs
• Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition
• Listen to Look: Action Recognition by Previewing Audio
• Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network
• Learning Where to Focus for Efficient Video Object Detection
• Hard-Attention for Scalable Image Classification
• Deep Q-Networks for Accelerating the Training of Deep Neural Networks
• Attention Control with Metric Learning Alignment for Image Set-based Recognition
• DeepSQLi: Deep Semantic Learning for Testing SQL Injection
• GASL: Guided Attention for Sparsity Learning in Deep Neural Networks
• Collaborative Attention Mechanism for Multi-View Action Recognition
• Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification
• "Factual" or "Emotional": Stylized Image Captioning with Adaptive Learning and Attention
• Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
• Fine-Grained Image Captioning with Global-Local Discriminative Objective
• Needles in Haystacks: On Classifying Tiny Objects in Large Images
• Cross-Modal Retrieval with Implicit Concept Association
• Active Information Acquisition
• Dynamic Capacity Networks
• Improving Deep Image Clustering With Spatial Transformer Layers
• Inter-slice image augmentation based on frame interpolation for boosting medical image segmentation accuracy
• CAR-Net: Clairvoyant Attentive Recurrent Network
• Gated Channel Transformation for Visual Recognition
• MBA-RainGAN: Multi-branch Attention Generative Adversarial Network for Mixture of Rain Removal from Single Images
• Deep Reinforcement Learning for Multi-Driver Vehicle Dispatching and Repositioning Problem
• Detection of Paroxysmal Atrial Fibrillation using Attention-based Bidirectional Recurrent Neural Networks
• A study of latent monotonic attention variants
• Semantic Object Parsing with Graph LSTM
• Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks
• The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
• Active Object Reconstruction Using a Guided View Planner
• Image Captioning Based on a Hierarchical Attention Mechanism and Policy Gradient Optimization
• Meta Feature Modulator for Long-tailed Recognition
• Attention and Localization based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging
• Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks
• An Attention-Gated Convolutional Neural Network for Sentence Classification
• Hybrid Attention-Based Transformer Block Model for Distant Supervision Relation Extraction
• Feature-based Attention in Convolutional Neural Networks
• Attention-based Image Upsampling
• Where to Look Next: Unsupervised Active Visual Exploration on 360° Input
• Look, Investigate, and Classify: A Deep Hybrid Attention Method for Breast Cancer Classification
• Towards Precise End-to-end Weakly Supervised Object Detection Network
• PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning
• Dual Recurrent Attention Units for Visual Question Answering
• Active Object Localization in Visual Situations
• Hide-and-Seek: A Template for Explainable AI
• AGIL: Learning Attention from Human for Visuomotor Tasks
• Visual Concept Recognition and Localization via Iterative Introspection
• Deep Online Convex Optimization with Gated Games
• Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain
• Teaching Machines to Converse
• Meta-Learning of Structured Task Distributions in Humans and Machines
• A Brand-level Ranking System with the Customized Attention-GRU Model
• Generalization and Robustness Implications in Object-Centric Learning
• Robust Image Matching By Dynamic Feature Selection
• Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity
• Maximizing Information Gain in Partially Observable Environments via Prediction Reward
• An Attention-Driven Approach of No-Reference Image Quality Assessment
• Benchmarking Unsupervised Object Representations for Video Sequences
• NEURO-DRAM: a 3D recurrent visual attention model for interpretable neuroimaging classification
• Attention Mechanisms for Object Recognition with Event-Based Cameras
• Focus of Attention Improves Information Transfer in Visual Features
• Locating Cephalometric X-Ray Landmarks with Foveated Pyramid Attention
• S3Net: A Single Stream Structure for Depth Guided Image Relighting
• Dual-attention Focused Module for Weakly Supervised Object Localization
• Joint Attention for Multi-Agent Coordination and Social Learning
• Active Perception and Representation for Robotic Manipulation
• Adaptive Focus for Efficient Video Recognition
• Improving unsupervised anomaly localization by applying multi-scale memories to autoencoders
• WordRank: Learning Word Embeddings via Robust Ranking
• End-to-End Speaker Height and age estimation using Attention Mechanism with LSTM-RNN
• DAWN: Dual Augmented Memory Network for Unsupervised Video Object Tracking
• A new rotating machinery fault diagnosis method based on the Time Series Transformer
• Dual-Attention Graph Convolutional Network
• Self Attention Grid for Person Re-Identification
• StampNet: unsupervised multi-class object discovery
• Convolutional Recurrent Residual U-Net Embedded with Attention Mechanism and Focal Tversky Loss Function for Cancerous Nuclei Detection
• GradNets: Dynamic Interpolation Between Neural Architectures
• Learning to Point and Count
• Visual Sensation and Perception Computational Models for Deep Learning: State of the art, Challenges and Prospects
• Multi-Layer Content Interaction Through Quaternion Product For Visual Question Answering
• Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
• DIANet: Dense-and-Implicit Attention Network
• Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs
• A Deep Decoder Structure Based on WordEmbedding Regression for An Encoder-Decoder Based Model for Image Captioning
• Reinforcement Learning To Adapt Speech Enhancement to Instantaneous Input Signal Quality
• A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
• Deep Features Analysis with Attention Networks
• Neural Machine Translation: A Review and Survey
• Action4D: Real-time Action Recognition in the Crowd and Clutter
• Not All Attention Is Needed: Gated Attention Network for Sequence Data
• Deep Reinforced Attention Learning for Quality-Aware Visual Recognition
• Collaborative Graph Walk for Semi-supervised Multi-Label Node Classification
• Neural Network Controller for Autonomous Pile Loading Revised
• Real-Time Resource Allocation for Tracking Systems
• MetaView: Few-shot Active Object Recognition
• Unlocking Pixels for Reinforcement Learning via Implicit Attention
• Spectral Attention-Driven Intelligent Target Signal Identification on a Wideband Spectrum
• Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning
• Temporally Identity-Aware SSD with Attentional LSTM
• Query-based Interactive Recommendation by Meta-Path and Adapted Attention-GRU
• Attention-based Transfer Learning for Brain-computer Interface
• Fine-Grained Object Detection over Scientific Document Images with Region Embeddings
• Gradient Importance Learning for Incomplete Observations
• Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams
• Where to Look: A Unified Attention Model for Visual Recognition with Reinforcement Learning
• Fake News Detection through Graph Comment Advanced Learning
• Unsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss
• Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks
• Saccadic Predictive Vision Model with a Fovea
• Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition
• Representation based and Attention augmented Meta learning
• Student's t-Generative Adversarial Networks
• Convolutional neural networks with extra-classical receptive fields
• Towards WARSHIP: Combining Components of Brain-Inspired Computing of RSH for Image Super Resolution
• Attention as a Perspective for Learning Tempo-invariant Audio Queries
• VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification
• Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization
• An Attention Model for group-level emotion recognition
• Explainable Neural Computation via Stack Neural Module Networks
• Explanation of Reinforcement Learning Model in Dynamic Multi-Agent System
• FPAN: Fine-grained and Progressive Attention Localization Network for Data Retrieval
• Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention
• FoveaTer: Foveated Transformer for Image Classification
• Hierarchical RNNs-Based Transformers MADDPG for Mixed Cooperative-Competitive Environments
• Unsupervised Object Learning via Common Fate
• Deep Contextual Recurrent Residual Networks for Scene Labeling
• Incorporating Reachability Knowledge into a Multi-Spatial Graph Convolution Based Seq2Seq Model for Traffic Forecasting
• Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks
• Understanding Character Recognition using Visual Explanations Derived from the Human Visual System and Deep Networks
• Recurrent Multimodal Interaction for Referring Image Segmentation
• Pareto Deterministic Policy Gradients and Its Application in 5G Massive MIMO Networks
• Modeling Human Reading with Neural Attention
• Visual Attention in Imaginative Agents
• Learning a Reinforced Agent for Flexible Exposure Bracketing Selection
• Visual Attention for Musical Instrument Recognition
• Neural Neighborhood Encoding for Classification
• Blur-Attention: A boosting mechanism for non-uniform blurred image restoration
• Selective Particle Attention: Visual Feature-Based Attention in Deep Reinforcement Learning
• Multi-scale Receptive Fields Graph Attention Network for Point Cloud Classification
• ASSD: Attentive Single Shot Multibox Detector
• A Controller-Recognizer Framework: How necessary is recognition for control?
• Segmentation-Aware and Adaptive Iris Recognition
• Joint Spatial and Layer Attention for Convolutional Networks
• Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization
• Master Thesis: Neural Sign Language Translation by Learning Tokenization
• ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition
• An Empirical Study on End-to-End Singing Voice Synthesis with Encoder-Decoder Architectures
• A Reinforcement Learning Approach for Sequential Spatial Transformer Networks
• Understanding top-down attention using task-oriented ablation design
• Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification
• Conditionally Learn to Pay Attention for Sequential Visual Task
• Sequential Coordination of Deep Models for Learning Visual Arithmetic
• Learning Good Representation via Continuous Attention
• On The Transferability of Deep-Q Networks
• Multi-FAN: Multi-Spectral Mosaic Super-Resolution Via Multi-Scale Feature Aggregation Network
• Active Object Localization with Deep Reinforcement Learning
• Learning sparse transformations through backpropagation
• SStaGCN: Simplified stacking based graph convolutional networks
• Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention
• KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation
• Understanding Information Processing in Human Brain by Interpreting Machine Learning Models
• Learning Fixation Point Strategy for Object Detection and Classification
• Recognizing Part Attributes with Insufficient Data
• Targeted Physical-World Attention Attack on Deep Learning Models in Road Sign Recognition
• Fast Unbalanced Optimal Transport on a Tree
• A Spatial and Temporal Features Mixture Model with Body Parts for Video-based Person Re-Identification
• Crowding in humans is unlike that in convolutional neural networks
• Testing Visual Attention in Dynamic Environments
• Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery
• Sidekick Policy Learning for Active Visual Exploration
• Learning spatial hearing via innate mechanisms
• Weakly Supervised Instance Segmentation by Deep Community Learning
• Hard Attention Control By Mutual Information Maximization
• Learning to Represent and Predict Sets with Deep Neural Networks
• Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classification
• Towards Viewpoint Invariant 3D Human Pose Estimation
• Sparsely ensembled convolutional neural network classifiers via reinforcement learning
• Recurrent 3D Attentional Networks for End-to-End Active Object Recognition
• Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations
• Summarizing Videos with Attention
• A novel sentence embedding based topic detection method for micro-blog
• Attention-Based LSTM Network for COVID-19 Clinical Trial Parsing
• Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss