{"total":33,"rows":[{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123,"area":null},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56,"area":null},{"id":"2210.07503","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","created":"2022-10-14","cited_by_count":43,"area":null},{"id":"2105.08141","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","created":"2021-05-17","cited_by_count":35,"area":null},{"id":"2112.03905","title":"ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints","created":"2021-12-07","cited_by_count":20,"area":null},{"id":"2212.05638","title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","created":"2022-12-12","cited_by_count":20,"area":null},{"id":"2311.18840","title":"Just Add $\\pi$! Pose Induced Video Transformers for Understanding Activities of Daily Living","created":"2023-11-30","cited_by_count":19,"area":null},{"id":"2104.09379","title":"BM-NAS: Bilevel Multimodal Neural Architecture Search","created":"2021-04-19","cited_by_count":13,"area":null},{"id":"2110.14994","title":"Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2205.15936","title":"Skeleton-based Action Recognition via Temporal-Channel Aggregation","created":"2022-05-31","cited_by_count":13,"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":"2406.09390","title":"LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2202.11374","title":"Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition","created":"2022-02-23","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":"2202.03283","title":"CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors","created":"2022-02-07","cited_by_count":5,"area":null},{"id":"2405.06574","title":"Deep video representation learning: a survey","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2506.03440","title":"Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2111.03993","title":"Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition","created":"2021-11-07","cited_by_count":2,"area":null},{"id":"2212.02649","title":"Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators","created":"2022-12-05","cited_by_count":2,"area":null},{"id":"2411.06553","title":"Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)","created":"2024-11-10","cited_by_count":2,"area":null},{"id":"2504.05076","title":"Content-Distortion High-Order Interaction for Blind Image Quality Assessment","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2110.07118","title":"Nuisance-Label Supervision: Robustness Improvement by Free Labels","created":"2021-10-14","cited_by_count":1,"area":null},{"id":"2210.13605","title":"GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2305.01733","title":"Cross-view Action Recognition via Contrastive View-invariant Representation","created":"2023-05-02","cited_by_count":1,"area":null},{"id":"2210.10247","title":"Performance of different machine learning methods on activity recognition and pose estimation datasets","created":"2022-10-19","cited_by_count":0,"area":null},{"id":"2212.09027","title":"2D Pose Estimation based Child Action Recognition","created":"2022-12-18","cited_by_count":0,"area":null},{"id":"2301.04842","title":"Towards High Performance One-Stage Human Pose Estimation","created":"2023-01-12","cited_by_count":0,"area":null},{"id":"2306.09331","title":"Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2410.22079","title":"HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2511.21202","title":"Towards an Effective Action-Region Tracking Framework for Fine-grained Video Action Recognition","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2602.10818","title":"Resource-Efficient RGB-Only Action Recognition for Edge Deployment","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.04509","title":"Recognition of Daily Activities through Multi-Modal Deep Learning: A Video, Pose, and Object-Aware Approach for Ambient Assisted Living","created":"2026-03-04","cited_by_count":0,"area":null}],"next_cursor":null}