{"total":143,"rows":[{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67,"area":null},{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59,"area":null},{"id":"2403.09508","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","created":"2024-03-14","cited_by_count":47,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"id":"2308.03063","title":"M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition","created":"2023-08-06","cited_by_count":34,"area":null},{"id":"2403.12534","title":"ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More","created":"2024-03-19","cited_by_count":33,"area":null},{"id":"2209.02399","title":"SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition","created":"2022-09-01","cited_by_count":29,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"area":null},{"id":"2305.12398","title":"Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition","created":"2023-05-21","cited_by_count":27,"area":null},{"id":"2409.05383","title":"Deep Learning for Video Anomaly Detection: A Review","created":"2024-09-09","cited_by_count":27,"area":null},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2210.00788","title":"Towards a Unified View on Visual Parameter-Efficient Transfer Learning","created":"2022-10-03","cited_by_count":25,"area":null},{"id":"2406.13327","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","created":"2024-06-19","cited_by_count":23,"area":null},{"id":"2405.10347","title":"Networking Systems for Video Anomaly Detection: A Tutorial and Survey","created":"2024-05-16","cited_by_count":21,"area":null},{"id":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19,"area":null},{"id":"2312.05719","title":"DVANet: Disentangling View and Action Features for Multi-View Action Recognition","created":"2023-12-10","cited_by_count":19,"area":null},{"id":"2202.02813","title":"A Coding Framework and Benchmark towards Low-Bitrate Video Understanding","created":"2022-02-06","cited_by_count":17,"area":null},{"id":"2207.03065","title":"Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition","created":"2022-07-07","cited_by_count":17,"area":null},{"id":"2404.08347","title":"Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworks","created":"2024-04-12","cited_by_count":16,"area":null},{"id":"2407.13930","title":"RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark","created":"2024-07-18","cited_by_count":16,"area":null},{"id":"2403.01560","title":"XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition","created":"2024-03-03","cited_by_count":15,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2408.09764","title":"Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms","created":"2024-08-19","cited_by_count":12,"area":null},{"id":"2308.13711","title":"EventTransAct: A video transformer-based framework for Event-camera based action recognition","created":"2023-08-25","cited_by_count":11,"area":null},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2403.10082","title":"CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner","created":"2024-03-15","cited_by_count":11,"area":null},{"id":"2407.14744","title":"A Comprehensive Review of Few-shot Action Recognition","created":"2024-07-20","cited_by_count":11,"area":null},{"id":"2411.14565","title":"Privacy-Preserving Video Anomaly Detection: A Survey","created":"2024-11-21","cited_by_count":11,"area":null},{"id":"2503.17132","title":"Temporal-Guided Spiking Neural Networks for Event-Based Human Action Recognition","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2109.05830","title":"Adversarial Bone Length Attack on Action Recognition","created":"2021-09-13","cited_by_count":10,"area":null},{"id":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2404.15349","title":"A Survey on Multimodal Wearable Sensor-based Human Action Recognition","created":"2024-04-14","cited_by_count":10,"area":null},{"id":"2406.06499","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2104.05018","title":"TedNet: A Pytorch Toolkit for Tensor Decomposition Networks","created":"2021-04-11","cited_by_count":9,"area":null},{"id":"2205.10071","title":"Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition","created":"2022-05-20","cited_by_count":9,"area":null},{"id":"2209.10073","title":"Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition","created":"2022-09-21","cited_by_count":9,"area":null},{"id":"2401.06150","title":"D-STGCNT: A Dense Spatio-Temporal Graph Conv-GRU Network based on transformer for assessment of patient physical rehabilitation","created":"2023-12-21","cited_by_count":9,"area":null},{"id":"2403.03037","title":"A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2410.14045","title":"Human Action Anticipation: A Survey","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2407.10860","title":"Human-Centric Transformer for Domain Adaptive Action Recognition","created":"2024-07-15","cited_by_count":8,"area":null},{"id":"2210.13827","title":"End-to-end Transformer for Compressed Video Quality Enhancement","created":"2022-10-25","cited_by_count":7,"area":null},{"id":"2405.15813","title":"From CNNs to Transformers in Multimodal Human Action Recognition: A Survey","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2409.02483","title":"TASAR: Transfer-based Attack on Skeletal Action Recognition","created":"2024-09-04","cited_by_count":7,"area":null},{"id":"2304.00858","title":"Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2308.11937","title":"Learning Bottleneck Transformer for Event Image-Voxel Feature Fusion based Classification","created":"2023-08-23","cited_by_count":6,"area":null},{"id":"2310.13039","title":"Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2312.06718","title":"Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2312.10930","title":"Deep Learning Approaches for Seizure Video Analysis: A Review","created":"2023-12-18","cited_by_count":6,"area":null},{"id":"2407.19497","title":"Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph","created":"2024-07-28","cited_by_count":6,"area":null},{"id":"2410.03302","title":"Action Selection Learning for Multi-label Multi-view Action Recognition","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2412.16233","title":"WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2506.00915","title":"3D Skeleton-Based Action Recognition: A Review","created":"2025-06-01","cited_by_count":6,"area":null},{"id":"2211.04253","title":"Eat-Radar: Continuous Fine-Grained Intake Gesture Detection Using FMCW Radar and 3D Temporal Convolutional Network with Attention","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2212.06206","title":"Contextual Explainable Video Representation: Human Perception-based Understanding","created":"2022-12-12","cited_by_count":5,"area":null},{"id":"2305.15283","title":"High Speed Human Action Recognition using a Photonic Reservoir Computer","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2402.02431","title":"Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2404.05490","title":"Two-Person Interaction Augmentation with Skeleton Priors","created":"2024-04-08","cited_by_count":5,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2412.13594","title":"Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2502.02487","title":"Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2208.09414","title":"ModSelect: Automatic Modality Selection for Synthetic-to-Real Domain Generalization","created":"2022-08-19","cited_by_count":4,"area":null},{"id":"2308.09322","title":"Audio-Visual Glance Network for Efficient Video Recognition","created":"2023-08-18","cited_by_count":4,"area":null},{"id":"2309.01262","title":"Multimodal Contrastive Learning with Hard Negative Sampling for Human Activity Recognition","created":"2023-09-03","cited_by_count":4,"area":null},{"id":"2403.15444","title":"A Survey of IMU Based Cross-Modal Transfer Learning in Human Activity Recognition","created":"2024-03-17","cited_by_count":4,"area":null},{"id":"2407.04587","title":"Multimodal Classification via Modal-Aware Interactive Enhancement","created":"2024-07-05","cited_by_count":4,"area":null},{"id":"2503.04470","title":"Gate-Shift-Pose: Enhancing Action Recognition in Sports with Skeleton Information","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2503.06522","title":"SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2504.02287","title":"MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2504.14301","title":"Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization","created":"2025-04-19","cited_by_count":4,"area":null},{"id":"2506.06631","title":"PhysLab: A Benchmark Dataset for Multi-Granularity Visual Parsing of Physics Experiments","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2506.11616","title":"Wi-CBR: Salient-aware Adaptive WiFi Sensing for Cross-domain Behavior Recognition","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2602.18043","title":"Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition","created":"2026-02-20","cited_by_count":4,"area":null},{"id":"2302.01921","title":"Transformers in Action Recognition: A Review on Temporal Modeling","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2308.14024","title":"Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition","created":"2023-08-27","cited_by_count":3,"area":null},{"id":"2406.04649","title":"SMART: Scene-motion-aware human action recognition framework for mental disorder group","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2406.18845","title":"Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2408.14441","title":"Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2506.09345","title":"An Effective End-to-End Solution for Multimodal Action Recognition","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2305.17939","title":"Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition","created":"2023-05-29","cited_by_count":2,"area":null},{"id":"2306.02739","title":"Knowledge-Driven Robot Program Synthesis from Human VR Demonstrations","created":"2023-06-05","cited_by_count":2,"area":null},{"id":"2309.01622","title":"Concepts is All You Need: A More Direct Path to AGI","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2312.07601","title":"Non-contact Multimodal Indoor Human Monitoring Systems: A Survey","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2401.10037","title":"Depth Over RGB: Automatic Evaluation of Open Surgery Skills Using Depth Camera","created":"2024-01-18","cited_by_count":2,"area":null},{"id":"2405.00712","title":"SoK: Behind the Accuracy of Complex Human Activity Recognition Using Deep Learning","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2406.03857","title":"MuJo: Multimodal Joint Feature Space Learning for Human Activity Recognition","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2406.16872","title":"Multi-channel Time Series Decomposition Network For Generalizable Sensor-Based Activity Recognition","created":"2024-03-28","cited_by_count":2,"area":null},{"id":"2407.01397","title":"Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2408.05421","title":"EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition","created":"2024-08-10","cited_by_count":2,"area":null},{"id":"2409.01879","title":"SPiKE: 3D Human Pose from Point Cloud Sequences","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2502.11858","title":"Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2502.13385","title":"SNN-Driven Multimodal Human Action Recognition via Sparse Spatial-Temporal Data Fusion","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2511.04042","title":"An LLM-based Framework for Human-Swarm Teaming Cognition in Disaster Search and Rescue","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2603.09798","title":"Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2608.15695","title":"Bitstream Action Recognition is Byte Modeling","created":"2026-08-16","cited_by_count":2,"area":null},{"id":"2209.13808","title":"Streaming Video Temporal Action Segmentation In Real Time","created":"2022-09-28","cited_by_count":1,"area":null},{"id":"2210.17412","title":"Adversarial Domain Adaptation for Action Recognition Around the Clock","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2212.14797","title":"Easing Automatic Neurorehabilitation via Classification and Smoothness Analysis","created":"2022-12-09","cited_by_count":1,"area":null},{"id":"2305.15692","title":"Deep Neural Networks in Video Human Action Recognition: A Review","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2309.06951","title":"TransNet: A Transfer Learning-Based Network for Human Action Recognition","created":"2023-09-13","cited_by_count":1,"area":null},{"id":"2403.14113","title":"Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition","created":"2024-03-21","cited_by_count":1,"area":null}],"next_cursor":"100"}