{"total":101,"rows":[{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193,"area":null},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96,"area":null},{"id":"2108.03656","title":"Skeleton-Contrastive 3D Action Representation Learning","created":"2021-08-08","cited_by_count":76,"area":null},{"id":"2408.02718","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","created":"2024-08-05","cited_by_count":67,"area":"mllm"},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53,"area":null},{"id":"2303.06242","title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","created":"2023-03-10","cited_by_count":44,"area":null},{"id":"2308.07092","title":"Masked Motion Predictors are Strong 3D Action Representation Learners","created":"2023-08-14","cited_by_count":41,"area":null},{"id":"2208.12448","title":"CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation","created":"2022-08-26","cited_by_count":38,"area":null},{"id":"2207.09644","title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","created":"2022-07-20","cited_by_count":30,"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":"2404.07487","title":"Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition","created":"2024-04-11","cited_by_count":19,"area":null},{"id":"2407.13460","title":"SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders","created":"2024-07-18","cited_by_count":19,"area":null},{"id":"2305.01074","title":"Physical Adversarial Attacks for Surveillance: A Survey","created":"2023-05-01","cited_by_count":15,"area":null},{"id":"2308.14500","title":"LAC: Latent Action Composition for Skeleton-based Action Segmentation","created":"2023-08-28","cited_by_count":15,"area":null},{"id":"2411.11288","title":"Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition","created":"2024-11-18","cited_by_count":13,"area":null},{"id":"2201.05761","title":"A Survey on RGB-D Datasets","created":"2022-01-15","cited_by_count":11,"area":null},{"id":"2309.05834","title":"SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition","created":"2023-09-11","cited_by_count":11,"area":null},{"id":"2405.20606","title":"Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning","created":"2024-05-31","cited_by_count":11,"area":null},{"id":"2202.03274","title":"Human Activity Recognition Using Tools of Convolutional Neural Networks: A State of the Art Review, Data Sets, Challenges and Future Prospects","created":"2022-02-02","cited_by_count":10,"area":null},{"id":"2403.10357","title":"ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D image","created":"2024-03-15","cited_by_count":9,"area":null},{"id":"2407.03817","title":"Markerless Multi-view 3D Human Pose Estimation: a survey","created":"2024-07-04","cited_by_count":9,"area":null},{"id":"2407.04190","title":"Computer Vision for Clinical Gait Analysis: A Gait Abnormality Video Dataset","created":"2024-07-05","cited_by_count":9,"area":null},{"id":"2411.10745","title":"Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition","created":"2024-11-16","cited_by_count":9,"area":"diffusion"},{"id":"2202.02232","title":"Bootstrapped Representation Learning for Skeleton-Based Action Recognition","created":"2022-02-04","cited_by_count":8,"area":null},{"id":"2403.17360","title":"Activity-Biometrics: Person Identification from Daily Activities","created":"2024-03-26","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":"2408.08671","title":"Towards Physical World Backdoor Attacks against Skeleton Action Recognition","created":"2024-08-16","cited_by_count":7,"area":null},{"id":"2302.12007","title":"DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition","created":"2023-02-22","cited_by_count":6,"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":"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":"2401.11790","title":"Deep Learning for Computer Vision based Activity Recognition and Fall Detection of the Elderly: a Systematic Review","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2401.15900","title":"MV2MAE: Multi-View Video Masked Autoencoders","created":"2024-01-29","cited_by_count":6,"area":null},{"id":"2406.18011","title":"Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation","created":"2024-06-26","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":"2506.22179","title":"Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition","created":"2025-06-27","cited_by_count":6,"area":null},{"id":"2508.04513","title":"Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation","created":"2025-08-06","cited_by_count":6,"area":null},{"id":"2107.05140","title":"Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction","created":"2021-07-11","cited_by_count":5,"area":null},{"id":"2306.11046","title":"FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2407.00521","title":"A Medical Low-Back Pain Physical Rehabilitation Dataset for Human Body Movement Analysis","created":"2024-06-29","cited_by_count":5,"area":null},{"id":"2207.05182","title":"Fine-grained Activities of People Worldwide","created":"2022-07-11","cited_by_count":4,"area":null},{"id":"2207.09767","title":"Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition","created":"2022-07-20","cited_by_count":4,"area":null},{"id":"2301.13360","title":"Skeleton-based Human Action Recognition via Convolutional Neural Networks (CNN)","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2403.03217","title":"Self-supervised 3D Patient Modeling with Multi-modal Attentive Fusion","created":"2024-03-05","cited_by_count":4,"area":null},{"id":"2410.17149","title":"Are Visual-Language Models Effective in Action Recognition? A Comparative Study","created":"2024-10-22","cited_by_count":4,"area":"mllm"},{"id":"2505.23012","title":"Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2111.11433","title":"Towards Tokenized Human Dynamics Representation","created":"2021-11-22","cited_by_count":3,"area":null},{"id":"2304.06977","title":"DeePoint: Visual Pointing Recognition and Direction Estimation","created":"2023-04-14","cited_by_count":3,"area":null},{"id":"2404.13657","title":"MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions","created":"2024-04-21","cited_by_count":3,"area":null},{"id":"2407.10935","title":"STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2408.09356","title":"Joint Temporal Pooling for Improving Skeleton-based Action Recognition","created":"2024-08-18","cited_by_count":3,"area":null},{"id":"2410.07153","title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2511.09388","title":"Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2512.11458","title":"Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation","created":"2025-12-12","cited_by_count":3,"area":null},{"id":"2603.18003","title":"Universal Skeleton Understanding via Differentiable Rendering and MLLMs","created":"2026-03-18","cited_by_count":3,"area":"lr"},{"id":"2603.29692","title":"SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2209.05077","title":"BON: An extended public domain dataset for human activity recognition","created":"2022-09-12","cited_by_count":2,"area":null},{"id":"2310.02422","title":"OneAdapt: Fast Configuration Adaptation for Video Analytics Applications via Backpropagation","created":"2023-10-03","cited_by_count":2,"area":null},{"id":"2401.00921","title":"Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence","created":"2024-01-01","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":"2409.09678","title":"A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities","created":"2024-09-15","cited_by_count":2,"area":null},{"id":"2410.06353","title":"Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2410.23641","title":"Recovering Complete Actions for Cross-dataset Skeleton Action Recognition","created":"2024-10-31","cited_by_count":2,"area":null},{"id":"2509.05543","title":"DuoCLR: Dual-Surrogate Contrastive Learning for Skeleton-based Human Action Segmentation","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2512.07136","title":"A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning","created":"2025-12-08","cited_by_count":2,"area":"lr"},{"id":"2604.09063","title":"Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition","created":"2026-04-10","cited_by_count":2,"area":"diffusion"},{"id":"2110.07993","title":"Pose-guided Generative Adversarial Net for Novel View Action Synthesis","created":"2021-10-15","cited_by_count":1,"area":null},{"id":"2209.11634","title":"View-Invariant Skeleton-based Action Recognition via Global-Local Contrastive Learning","created":"2022-09-23","cited_by_count":1,"area":null},{"id":"2303.08463","title":"Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2304.04023","title":"Attack-Augmentation Mixing-Contrastive Skeletal Representation Learning","created":"2023-04-08","cited_by_count":1,"area":null},{"id":"2308.01035","title":"TS-RGBD Dataset: a Novel Dataset for Theatre Scenes Description for People with Visual Impairments","created":"2023-08-02","cited_by_count":1,"area":null},{"id":"2309.11445","title":"SkeleTR: Towrads Skeleton-based Action Recognition in the Wild","created":"2023-09-20","cited_by_count":1,"area":null},{"id":"2309.15635","title":"Position and Orientation-Aware One-Shot Learning for Medical Action Recognition from Signal Data","created":"2023-09-27","cited_by_count":1,"area":null},{"id":"2310.15568","title":"I$^2$MD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation","created":"2023-10-24","cited_by_count":1,"area":null},{"id":"2406.16638","title":"Feature Fusion for Human Activity Recognition using Parameter-Optimized Multi-Stage Graph Convolutional Network and Transformer Models","created":"2024-06-24","cited_by_count":1,"area":null},{"id":"2502.16493","title":"Trunk-branch Contrastive Network with Multi-view Deformable Aggregation for Multi-view Action Recognition","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2510.09731","title":"Multi Camera Connected Vision System with Multi View Analytics: A Comprehensive Survey","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2512.03837","title":"Heatmap Pooling Network for Action Recognition from RGB Videos","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2512.11941","title":"DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2601.10521","title":"BikeActions: An Open Platform and Benchmark for Cyclist-Centric VRU Action Recognition","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2101.08851","title":"Bridging the gap between Human Action Recognition and Online Action Detection","created":"2021-01-21","cited_by_count":0,"area":"distill"},{"id":"2108.03329","title":"Feature-Supervised Action Modality Transfer","created":"2021-08-06","cited_by_count":0,"area":null},{"id":"2307.13541","title":"Group Activity Recognition in Computer Vision: A Comprehensive Review, Challenges, and Future Perspectives","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2308.15345","title":"IndGIC: Supervised Action Recognition under Low Illumination","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2406.01662","title":"Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2408.16442","title":"Integrating Features for Recognizing Human Activities through Optimized Parameters in Graph Convolutional Networks and Transformer Architectures","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2409.17951","title":"Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action Recognition","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2412.14833","title":"Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action Recognition","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2508.12948","title":"MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2511.14179","title":"DoGCLR: Dominance-Game Contrastive Learning Network for Skeleton-Based Action Recognition","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2601.16694","title":"Affinity Contrastive Learning for Skeleton-based Human Activity Understanding","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2601.17194","title":"Decoding Psychological States Through Movement: Inferring Human Kinesic Functions with Application to Built Environments","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2603.09367","title":"M3GCLR: Multi-View Mini-Max Infinite Skeleton-Data Game Contrastive Learning For Skeleton-Based Action Recognition","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.26400","title":"SHANDS: A Multi-View Dataset and Benchmark for Surgical Hand-Gesture and Error Recognition Toward Medical Training","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.11497","title":"PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.20838","title":"USV: Towards Understanding the User-generated Short-form Videos","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.22695","title":"Improving Viewpoint-Invariance and Temporal Consistency for Action Detection","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.21607","title":"T-MOR: Learning Motion-Aware Skeleton Representations for Human Action Recognition","created":"2026-06-19","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}