{"total":349,"rows":[{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252,"area":null},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125,"area":null},{"id":"2108.08728","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","created":"2021-08-19","cited_by_count":114,"area":null},{"id":"2105.02358","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","created":"2021-05-05","cited_by_count":109,"area":null},{"id":"2308.08708","title":"Consciousness in Artificial Intelligence: Insights from the Science of Consciousness","created":"2023-08-17","cited_by_count":104,"area":null},{"id":"2311.11829","title":"System 2 Attention (is something you might need too)","created":"2023-11-20","cited_by_count":89,"area":null},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"area":null},{"id":"2108.08782","title":"Causal Attention for Unbiased Visual Recognition","created":"2021-08-19","cited_by_count":80,"area":null},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77,"area":null},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2306.17100","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","created":"2023-06-29","cited_by_count":71,"area":null},{"id":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"area":null},{"id":"2301.00557","title":"Learning to Maximize Mutual Information for Dynamic Feature Selection","created":"2023-01-02","cited_by_count":56,"area":null},{"id":"2212.09522","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","created":"2022-12-19","cited_by_count":55,"area":null},{"id":"2312.16475","title":"Federated Continual Learning via Knowledge Fusion: A Survey","created":"2023-12-27","cited_by_count":53,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2107.10189","title":"DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation","created":"2021-07-21","cited_by_count":46,"area":null},{"id":"2410.01104","title":"Softmax is not Enough (for Sharp Size Generalisation)","created":"2024-10-01","cited_by_count":46,"area":null},{"id":"2108.01684","title":"Vision Transformer with Progressive Sampling","created":"2021-08-03","cited_by_count":44,"area":null},{"id":"2108.12204","title":"This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation","created":"2021-08-27","cited_by_count":43,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2108.05720","title":"Semantic Concentration for Domain Adaptation","created":"2021-08-12","cited_by_count":42,"area":null},{"id":"2201.03014","title":"Glance and Focus Networks for Dynamic Visual Recognition","created":"2022-01-09","cited_by_count":41,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2201.03746","title":"TSA-Net: Tube Self-Attention Network for Action Quality Assessment","created":"2022-01-11","cited_by_count":36,"area":null},{"id":"2209.10218","title":"HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classification","created":"2022-09-21","cited_by_count":30,"area":null},{"id":"2110.06562","title":"Unsupervised Object Learning via Common Fate","created":"2021-10-13","cited_by_count":29,"area":null},{"id":"2203.01824","title":"LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network","created":"2022-03-03","cited_by_count":29,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2105.14173","title":"FoveaTer: Foveated Transformer for Image Classification","created":"2021-05-29","cited_by_count":28,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2306.06722","title":"$E(2)$-Equivariant Vision Transformer","created":"2023-06-11","cited_by_count":27,"area":null},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2309.01439","title":"Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN","created":"2023-09-04","cited_by_count":25,"area":null},{"id":"2103.00375","title":"Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control","created":"2021-02-28","cited_by_count":24,"area":"offlinerl"},{"id":"2106.03921","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning","created":"2021-06-07","cited_by_count":23,"area":null},{"id":"2307.07527","title":"Machine Learning for Autonomous Vehicle's Trajectory Prediction: A comprehensive survey, Challenges, and Future Research Directions","created":"2023-07-12","cited_by_count":23,"area":"driving"},{"id":"2303.09992","title":"LION: Implicit Vision Prompt Tuning","created":"2023-03-17","cited_by_count":22,"area":null},{"id":"2505.05522","title":"Continuous Thought Machines","created":"2025-05-08","cited_by_count":22,"area":null},{"id":"2111.01628","title":"Human Attention in Fine-grained Classification","created":"2021-11-02","cited_by_count":21,"area":null},{"id":"2112.04632","title":"Recurrent Glimpse-based Decoder for Detection with Transformer","created":"2021-12-09","cited_by_count":21,"area":null},{"id":"2306.03301","title":"Estimating Conditional Mutual Information for Dynamic Feature Selection","created":"2023-06-05","cited_by_count":21,"area":null},{"id":"2112.04488","title":"A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolution","created":"2021-12-08","cited_by_count":19,"area":null},{"id":"2302.13960","title":"Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition","created":"2023-02-27","cited_by_count":19,"area":null},{"id":"2102.10212","title":"Hard-Attention for Scalable Image Classification","created":"2021-02-20","cited_by_count":18,"area":null},{"id":"2104.04192","title":"Reinforced Attention for Few-Shot Learning and Beyond","created":"2021-04-09","cited_by_count":18,"area":null},{"id":"2211.02831","title":"Deep Face Restoration: A Survey","created":"2022-11-05","cited_by_count":17,"area":null},{"id":"2211.10763","title":"PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection","created":"2022-11-19","cited_by_count":17,"area":null},{"id":"2108.04186","title":"Pose is all you need: The pose only group activity recognition system (POGARS)","created":"2021-08-09","cited_by_count":16,"area":null},{"id":"2202.08557","title":"CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving","created":"2022-02-17","cited_by_count":16,"area":"driving"},{"id":"2204.12406","title":"A survey on attention mechanisms for medical applications: are we moving towards better algorithms?","created":"2022-04-26","cited_by_count":15,"area":null},{"id":"2509.15333","title":"Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception","created":"2025-09-18","cited_by_count":15,"area":null},{"id":"2101.06636","title":"Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition","created":"2021-01-17","cited_by_count":14,"area":null},{"id":"2106.15686","title":"Attention Aware Wavelet-based Detection of Morphed Face Images","created":"2021-06-29","cited_by_count":14,"area":null},{"id":"2302.00270","title":"Internally Rewarded Reinforcement Learning","created":"2023-02-01","cited_by_count":14,"area":"alignment"},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2201.02143","title":"Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks","created":"2022-01-06","cited_by_count":13,"area":null},{"id":"2211.05039","title":"Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task","created":"2022-11-09","cited_by_count":13,"area":null},{"id":"2407.00118","title":"From Efficient Multimodal Models to World Models: A Survey","created":"2024-06-27","cited_by_count":13,"area":"wm"},{"id":"2108.05340","title":"Person Re-identification via Attention Pyramid","created":"2021-08-11","cited_by_count":12,"area":null},{"id":"2111.07534","title":"A Probabilistic Hard Attention Model For Sequentially Observed Scenes","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2112.15509","title":"Scene-Adaptive Attention Network for Crowd Counting","created":"2021-12-31","cited_by_count":12,"area":null},{"id":"2206.04928","title":"GAMR: A Guided Attention Model for (visual) Reasoning","created":"2022-06-10","cited_by_count":12,"area":"lr"},{"id":"2310.13849","title":"A Dual-Stream Neural Network Explains the Functional Segregation of Dorsal and Ventral Visual Pathways in Human Brains","created":"2023-10-20","cited_by_count":12,"area":null},{"id":"2105.04181","title":"KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation","created":"2021-05-10","cited_by_count":11,"area":"distill"},{"id":"2204.00656","title":"Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes","created":"2022-04-01","cited_by_count":11,"area":null},{"id":"2107.07013","title":"Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity","created":"2021-07-14","cited_by_count":10,"area":null},{"id":"2202.06268","title":"BViT: Broad Attention based Vision Transformer","created":"2022-02-13","cited_by_count":10,"area":null},{"id":"2208.09795","title":"Stop&Hop: Early Classification of Irregular Time Series","created":"2022-08-21","cited_by_count":10,"area":null},{"id":"2209.12164","title":"Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward","created":"2022-09-25","cited_by_count":10,"area":null},{"id":"2210.13461","title":"Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning","created":"2022-10-23","cited_by_count":10,"area":"wm"},{"id":"2103.11744","title":"Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling","created":"2021-03-22","cited_by_count":9,"area":null},{"id":"2105.00681","title":"S3Net: A Single Stream Structure for Depth Guided Image Relighting","created":"2021-05-03","cited_by_count":9,"area":null},{"id":"2108.11717","title":"Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration","created":"2021-08-26","cited_by_count":9,"area":null},{"id":"2304.03768","title":"SparseFormer: Sparse Visual Recognition via Limited Latent Tokens","created":"2023-04-07","cited_by_count":9,"area":null},{"id":"2312.01060","title":"Spectrum-driven Mixed-frequency Network for Hyperspectral Salient Object Detection","created":"2023-12-02","cited_by_count":9,"area":null},{"id":"2412.11228","title":"Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition","created":"2024-12-15","cited_by_count":9,"area":null},{"id":"2508.01957","title":"Stochastic Encodings for Active Feature Acquisition","created":"2025-08-03","cited_by_count":9,"area":null},{"id":"2101.02843","title":"Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction","created":"2021-01-08","cited_by_count":8,"area":null},{"id":"2104.07750","title":"Joint Attention for Multi-Agent Coordination and Social Learning","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2112.05909","title":"Neural Attention Models in Deep Learning: Survey and Taxonomy","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2201.02628","title":"Attention Option-Critic","created":"2022-01-07","cited_by_count":8,"area":null},{"id":"2205.08780","title":"Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving","created":"2022-05-18","cited_by_count":8,"area":null},{"id":"2205.13780","title":"Text-Based Automatic Personality Prediction Using KGrAt-Net; A Knowledge Graph Attention Network Classifier","created":"2022-05-27","cited_by_count":8,"area":null},{"id":"2210.16584","title":"Interpretable CNN-Multilevel Attention Transformer for Rapid Recognition of Pneumonia from Chest X-Ray Images","created":"2022-10-29","cited_by_count":8,"area":null},{"id":"2302.10473","title":"Oriented object detection in optical remote sensing images using deep learning: a survey","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2310.14576","title":"Tensor Decomposition Based Attention Module for Spiking Neural Networks","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2311.01419","title":"C3DM: Constrained-Context Conditional Diffusion Models for Imitation Learning","created":"2023-11-02","cited_by_count":8,"area":"diffusion"},{"id":"2311.15543","title":"Beyond Pixels: Exploring Human-Readable SVG Generation for Simple Images with Vision Language Models","created":"2023-11-27","cited_by_count":8,"area":"mllm"},{"id":"2312.01450","title":"Foveation in the Era of Deep Learning","created":"2023-12-03","cited_by_count":8,"area":null},{"id":"2402.12241","title":"Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis","created":"2024-02-19","cited_by_count":8,"area":null},{"id":"2405.18221","title":"Recurrent Natural Policy Gradient for POMDPs","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2406.00480","title":"AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning","created":"2024-06-01","cited_by_count":8,"area":null}],"next_cursor":"100"}