{"total":126,"rows":[{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257,"area":null},{"id":"2104.14466","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","created":"2021-04-29","cited_by_count":106,"area":null},{"id":"2112.03590","title":"Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition","created":"2021-12-07","cited_by_count":90,"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":"2108.01959","title":"Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning","created":"2021-08-04","cited_by_count":58,"area":null},{"id":"2204.07346","title":"MVSTER: Epipolar Transformer for Efficient Multi-View Stereo","created":"2022-04-15","cited_by_count":50,"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":"2404.00532","title":"LLMs are Good Action Recognizers","created":"2024-03-31","cited_by_count":37,"area":null},{"id":"2211.09590","title":"Hypergraph Transformer for Skeleton-based Action Recognition","created":"2022-11-17","cited_by_count":36,"area":null},{"id":"2209.09484","title":"Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos","created":"2022-09-20","cited_by_count":35,"area":null},{"id":"2208.03497","title":"Contrastive Positive Mining for Unsupervised 3D Action Representation Learning","created":"2022-08-06","cited_by_count":34,"area":null},{"id":"2207.12100","title":"IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition","created":"2022-07-25","cited_by_count":31,"area":null},{"id":"2211.13466","title":"Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations","created":"2022-11-24","cited_by_count":31,"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":"2112.04178","title":"Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition","created":"2021-12-08","cited_by_count":29,"area":null},{"id":"2111.13089","title":"GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition","created":"2021-11-25","cited_by_count":27,"area":null},{"id":"2305.08953","title":"Motion Question Answering via Modular Motion Programs","created":"2023-05-15","cited_by_count":27,"area":"lr"},{"id":"2103.05266","title":"BASAR:Black-box Attack on Skeletal Action Recognition","created":"2021-03-09","cited_by_count":26,"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":"2302.09018","title":"Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences","created":"2023-02-17","cited_by_count":25,"area":null},{"id":"2103.05347","title":"Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack","created":"2021-03-09","cited_by_count":24,"area":null},{"id":"2202.04075","title":"Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition","created":"2022-02-08","cited_by_count":24,"area":null},{"id":"2308.03950","title":"Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization","created":"2023-08-07","cited_by_count":24,"area":null},{"id":"2110.11191","title":"Generative Adversarial Graph Convolutional Networks for Human Action Synthesis","created":"2021-10-21","cited_by_count":23,"area":null},{"id":"2210.16820","title":"Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition","created":"2022-10-30","cited_by_count":22,"area":null},{"id":"2305.00666","title":"Part Aware Contrastive Learning for Self-Supervised Action Recognition","created":"2023-05-01","cited_by_count":21,"area":null},{"id":"2308.03975","title":"Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning","created":"2023-08-08","cited_by_count":19,"area":null},{"id":"2103.16516","title":"Recognizing Actions in Videos from Unseen Viewpoints","created":"2021-03-30","cited_by_count":18,"area":null},{"id":"2210.02693","title":"Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition","created":"2022-10-06","cited_by_count":18,"area":null},{"id":"2302.02316","title":"Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition","created":"2023-02-05","cited_by_count":17,"area":null},{"id":"2312.06330","title":"Navigating Open Set Scenarios for Skeleton-based Action Recognition","created":"2023-12-11","cited_by_count":17,"area":null},{"id":"2304.08799","title":"Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization","created":"2023-04-18","cited_by_count":16,"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":"2404.07645","title":"Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos","created":"2024-04-11","cited_by_count":13,"area":"ssm"},{"id":"2211.10412","title":"Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey","created":"2022-11-17","cited_by_count":12,"area":null},{"id":"2307.07286","title":"One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching","created":"2023-07-14","cited_by_count":12,"area":null},{"id":"2407.15706","title":"Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition","created":"2024-07-22","cited_by_count":12,"area":"mllm"},{"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":"2112.12668","title":"3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na\\\"ive","created":"2021-12-23","cited_by_count":10,"area":null},{"id":"2308.05681","title":"Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient","created":"2023-08-10","cited_by_count":10,"area":null},{"id":"2112.10570","title":"Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition","created":"2021-12-20","cited_by_count":9,"area":null},{"id":"2207.09675","title":"ERA: Expert Retrieval and Assembly for Early Action Prediction","created":"2022-07-20","cited_by_count":9,"area":null},{"id":"2301.11495","title":"Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks","created":"2023-01-27","cited_by_count":9,"area":null},{"id":"2107.07089","title":"STAR: Sparse Transformer-based Action Recognition","created":"2021-07-15","cited_by_count":8,"area":null},{"id":"2202.02232","title":"Bootstrapped Representation Learning for Skeleton-Based Action Recognition","created":"2022-02-04","cited_by_count":8,"area":null},{"id":"2305.11468","title":"Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2211.11312","title":"Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack","created":"2022-11-21","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":"2408.08671","title":"Towards Physical World Backdoor Attacks against Skeleton Action Recognition","created":"2024-08-16","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":"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":"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":"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":"2407.12312","title":"Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition","created":"2024-07-17","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":"2202.07308","title":"HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment","created":"2022-02-15","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":"2208.08599","title":"Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition","created":"2022-08-18","cited_by_count":4,"area":null},{"id":"2209.02986","title":"Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition","created":"2022-09-07","cited_by_count":4,"area":null},{"id":"2209.11582","title":"Pose-Aided Video-based Person Re-Identification via Recurrent Graph Convolutional Network","created":"2022-09-23","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":"2405.06574","title":"Deep video representation learning: a survey","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2411.05692","title":"Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2505.20920","title":"HuMoCon: Concept Discovery for Human Motion Understanding","created":"2025-05-27","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":"2205.14405","title":"Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns","created":"2022-05-28","cited_by_count":3,"area":null},{"id":"2208.03444","title":"AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement","created":"2022-08-06","cited_by_count":3,"area":null},{"id":"2305.19480","title":"Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2310.10131","title":"3DYoga90: A Hierarchical Video Dataset for Yoga Pose Understanding","created":"2023-10-16","cited_by_count":3,"area":null},{"id":"2401.00409","title":"A Two-stream Hybrid CNN-Transformer Network for Skeleton-based Human Interaction Recognition","created":"2023-12-31","cited_by_count":3,"area":null},{"id":"2411.00128","title":"Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2105.06711","title":"REGINA - Reasoning Graph Convolutional Networks in Human Action Recognition","created":"2021-05-14","cited_by_count":2,"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":"2111.11250","title":"Action Recognition with Domain Invariant Features of Skeleton Image","created":"2021-11-19","cited_by_count":2,"area":null},{"id":"2305.02324","title":"Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition","created":"2023-05-03","cited_by_count":2,"area":null},{"id":"2306.17574","title":"SpATr: MoCap 3D Human Action Recognition based on Spiral Auto-encoder and Transformer Network","created":"2023-06-30","cited_by_count":2,"area":null},{"id":"2307.07791","title":"Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2403.07354","title":"BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin","created":"2024-03-12","cited_by_count":2,"area":null},{"id":"2404.18206","title":"Enhancing Action Recognition from Low-Quality Skeleton Data via Part-Level Knowledge Distillation","created":"2024-04-28","cited_by_count":2,"area":"distill"},{"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":"2407.14655","title":"LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition","created":"2024-07-19","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":"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":"2112.09413","title":"Self-attention based anchor proposal for skeleton-based action recognition","created":"2021-12-17","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":"2305.01733","title":"Cross-view Action Recognition via Contrastive View-invariant Representation","created":"2023-05-02","cited_by_count":1,"area":null},{"id":"2305.08191","title":"Is end-to-end learning enough for fitness activity recognition?","created":"2023-05-14","cited_by_count":1,"area":null},{"id":"2306.14313","title":"A Closer Look at Geometric Temporal Dynamics for Face Anti-Spoofing","created":"2023-06-25","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":"2407.01375","title":"Transferable-guided Attention Is All You Need for Video Domain Adaptation","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2408.02855","title":"Analyzing Data Efficiency and Performance of Machine Learning Algorithms for Assessing Low Back Pain Physical Rehabilitation Exercises","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2504.13866","title":"Skeleton-Based Transformer for Classification of Errors and Better Feedback in Low Back Pain Physical Rehabilitation Exercises","created":"2025-03-28","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":"2101.08851","title":"Bridging the gap between Human Action Recognition and Online Action Detection","created":"2021-01-21","cited_by_count":0,"area":"distill"}],"next_cursor":"100"}