{"total":102,"rows":[{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117,"area":null},{"id":"2103.08833","title":"Skeleton Aware Multi-modal Sign Language Recognition","created":"2021-03-16","cited_by_count":101,"area":null},{"id":"2106.15125","title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","created":"2021-06-29","cited_by_count":87,"area":null},{"id":"2208.10741","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2022-08-23","cited_by_count":85,"area":null},{"id":"2205.09443","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","created":"2022-05-19","cited_by_count":83,"area":null},{"id":"2206.13028","title":"Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition","created":"2022-06-27","cited_by_count":71,"area":null},{"id":"2112.13715","title":"SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos","created":"2021-12-27","cited_by_count":64,"area":null},{"id":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","cited_by_count":63,"area":null},{"id":"2108.07181","title":"Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation","created":"2021-08-16","cited_by_count":62,"area":null},{"id":"2108.01959","title":"Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning","created":"2021-08-04","cited_by_count":58,"area":null},{"id":"2104.11536","title":"Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective","created":"2021-04-23","cited_by_count":50,"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":"2107.08580","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","created":"2021-07-19","cited_by_count":35,"area":null},{"id":"2110.05877","title":"OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages","created":"2021-10-12","cited_by_count":31,"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":"2210.05895","title":"DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition","created":"2022-10-12","cited_by_count":26,"area":null},{"id":"2108.04536","title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","created":"2021-08-10","cited_by_count":25,"area":null},{"id":"2307.10624","title":"Joint Skeletal and Semantic Embedding Loss for Micro-gesture Classification","created":"2023-07-20","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":"2112.03905","title":"ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints","created":"2021-12-07","cited_by_count":20,"area":null},{"id":"2202.01727","title":"Skeleton-Based Action Segmentation with Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks","created":"2022-02-03","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":"2408.03097","title":"Prototype Learning for Micro-gesture Classification","created":"2024-08-06","cited_by_count":18,"area":null},{"id":"2110.06161","title":"Sign Language Recognition via Skeleton-Aware Multi-Model Ensemble","created":"2021-10-12","cited_by_count":16,"area":null},{"id":"2212.04761","title":"Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition","created":"2022-12-09","cited_by_count":13,"area":null},{"id":"2108.08633","title":"Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2411.14796","title":"Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections","created":"2024-11-22","cited_by_count":11,"area":null},{"id":"2507.21977","title":"Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition","created":"2025-07-29","cited_by_count":11,"area":null},{"id":"2212.12857","title":"StepNet: Spatial-temporal Part-aware Network for Isolated Sign Language Recognition","created":"2022-12-25","cited_by_count":9,"area":null},{"id":"2308.14492","title":"PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Clouds","created":"2023-08-28","cited_by_count":9,"area":null},{"id":"2203.11009","title":"Continual Spatio-Temporal Graph Convolutional Networks","created":"2022-03-21","cited_by_count":8,"area":null},{"id":"2312.05830","title":"A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation","created":"2023-12-10","cited_by_count":8,"area":null},{"id":"2208.06174","title":"Two-person Graph Convolutional Network for Skeleton-based Human Interaction Recognition","created":"2022-08-12","cited_by_count":7,"area":null},{"id":"2308.07571","title":"Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2202.02212","title":"Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2406.10501","title":"Self-Supervised Representation Learning with Spatial-Temporal Consistency for Sign Language Recognition","created":"2024-06-15","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":"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":"2311.14775","title":"VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG","created":"2023-11-24","cited_by_count":5,"area":null},{"id":"2404.10210","title":"MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition","created":"2024-04-16","cited_by_count":5,"area":null},{"id":"2505.10679","title":"Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?","created":"2025-05-15","cited_by_count":5,"area":null},{"id":"2208.08599","title":"Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition","created":"2022-08-18","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":"2303.00952","title":"Towards Activated Muscle Group Estimation in the Wild","created":"2023-03-02","cited_by_count":4,"area":null},{"id":"2403.12519","title":"Dynamic Spatial-Temporal Aggregation for Skeleton-Aware Sign Language Recognition","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2403.14534","title":"Transfer Learning for Cross-dataset Isolated Sign Language Recognition in Under-Resourced Datasets","created":"2024-03-21","cited_by_count":4,"area":null},{"id":"2405.06574","title":"Deep video representation learning: a survey","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2503.11004","title":"VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2510.25345","title":"Informative Sample Selection Model for Skeleton-based Action Recognition with Limited Training Samples","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2106.15989","title":"Word-level Sign Language Recognition with Multi-stream Neural Networks Focusing on Local Regions and Skeletal Information","created":"2021-06-30","cited_by_count":3,"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":"2403.15212","title":"GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2409.18481","title":"Deep Heterogeneous Contrastive Hyper-Graph Learning for In-the-Wild Context-Aware Human Activity Recognition","created":"2024-09-27","cited_by_count":3,"area":null},{"id":"2104.05015","title":"Temporal Consistency Two-Stream CNN for Human Motion Prediction","created":"2021-04-11","cited_by_count":2,"area":null},{"id":"2201.06304","title":"Action Keypoint Network for Efficient Video Recognition","created":"2022-01-17","cited_by_count":2,"area":null},{"id":"2207.12648","title":"Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter- and Intra-body Graphs","created":"2022-07-26","cited_by_count":2,"area":null},{"id":"2308.12049","title":"Towards Privacy-Supporting Fall Detection via Deep Unsupervised RGB2Depth Adaptation","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2402.08401","title":"LOSS-GAT: Label Propagation and One-Class Semi-Supervised Graph Attention Network for Fake News Detection","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2503.23214","title":"Action Recognition in Real-World Ambient Assisted Living Environment","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2505.10810","title":"MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human Motion Generation","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2603.16943","title":"KGS-GCN: Kinematics-Driven Gaussian Splatting and Probabilistic Topology for Skeleton-Based Action Recognition","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2111.00823","title":"LSTA-Net: Long short-term Spatio-Temporal Aggregation Network for Skeleton-based Action Recognition","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2201.01603","title":"Deep Probabilistic Graph Matching","created":"2022-01-05","cited_by_count":1,"area":null},{"id":"2208.09150","title":"Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2210.06192","title":"Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2022-10-10","cited_by_count":1,"area":null},{"id":"2212.10746","title":"SLGTformer: An Attention-Based Approach to Sign Language Recognition","created":"2022-12-21","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":"2401.11783","title":"Full-Body Motion Reconstruction with Sparse Sensing from Graph Perspective","created":"2024-01-22","cited_by_count":1,"area":null},{"id":"2403.02772","title":"Rehabilitation Exercise Quality Assessment through Supervised Contrastive Learning with Hard and Soft Negatives","created":"2024-03-05","cited_by_count":1,"area":null},{"id":"2411.19544","title":"SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders","created":"2024-11-29","cited_by_count":1,"area":null},{"id":"2501.03290","title":"A Decision-Based Heterogenous Graph Attention Network for Multi-Class Fake News Detection","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2502.14939","title":"Online hand gesture recognition using Continual Graph Transformers","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2507.03936","title":"Learning Adaptive Node Selection with External Attention for Human Interaction Recognition","created":"2025-07-05","cited_by_count":1,"area":null},{"id":"2509.21261","title":"Every Subtlety Counts: Fine-grained Person Independence Micro-Action Recognition via Distributionally Robust Optimization","created":"2025-09-25","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":"2512.21064","title":"Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2512.23291","title":"Multi-Track Multimodal Learning on iMiGUE: Micro-Gesture and Emotion Recognition","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2604.02616","title":"Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2206.03061","title":"Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2206.15002","title":"Spatial Transformer Network with Transfer Learning for Small-scale Fine-grained Skeleton-based Tai Chi Action Recognition","created":"2022-06-30","cited_by_count":0,"area":null},{"id":"2212.09013","title":"Graph Neural Network based Child Activity Recognition","created":"2022-12-18","cited_by_count":0,"area":null},{"id":"2301.13090","title":"Action Capsules: Human Skeleton Action Recognition","created":"2023-01-30","cited_by_count":0,"area":null},{"id":"2302.12967","title":"Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition","created":"2023-02-25","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":"2307.11973","title":"Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition","created":"2023-07-22","cited_by_count":0,"area":null},{"id":"2402.14400","title":"Learning Developmental Age from 3D Infant Kinetics Using Adaptive Graph Neural Networks","created":"2024-02-22","cited_by_count":0,"area":null},{"id":"2404.02624","title":"Multi-Scale Spatial-Temporal Self-Attention Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2410.21300","title":"Contrastive Learning with Auxiliary User Detection for Identifying Activities","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2411.12560","title":"Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2501.05066","title":"Improving Skeleton-based Action Recognition with Interactive Object Information","created":"2025-01-09","cited_by_count":0,"area":null},{"id":"2505.18048","title":"SHARDeg: A Benchmark for Skeletal Human Action Recognition in Degraded Scenarios","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2601.07666","title":"Variational Contrastive Learning for Skeleton-based Action Recognition","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2604.03590","title":"SBF: An Effective Representation to Augment Skeleton for Video-based Human Action Recognition","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.21011","title":"Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.22839","title":"From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2606.30309","title":"A Point Cloud Transformer for Remote Monitoring and Automated Assessment of Physical Rehabilitation Exercises","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.17121","title":"Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.05115","title":"Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":"100"}