{"total":105,"rows":[{"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":"2303.14526","title":"Selective Structured State-Spaces for Long-Form Video Understanding","created":"2023-03-25","cited_by_count":105,"area":"ssm"},{"id":"2108.03656","title":"Skeleton-Contrastive 3D Action Representation Learning","created":"2021-08-08","cited_by_count":76,"area":null},{"id":"2303.17220","title":"Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys","created":"2023-03-30","cited_by_count":75,"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":"2107.00285","title":"iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis","created":"2021-07-01","cited_by_count":63,"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":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"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":"2306.05526","title":"Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment","created":"2023-06-08","cited_by_count":46,"area":null},{"id":"2208.05318","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","created":"2022-08-10","cited_by_count":43,"area":null},{"id":"2211.09590","title":"Hypergraph Transformer for Skeleton-based Action Recognition","created":"2022-11-17","cited_by_count":36,"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":"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":"2207.12100","title":"IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition","created":"2022-07-25","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":"2212.02082","title":"Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning","created":"2022-12-05","cited_by_count":30,"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":"2110.11191","title":"Generative Adversarial Graph Convolutional Networks for Human Action Synthesis","created":"2021-10-21","cited_by_count":23,"area":null},{"id":"2212.04638","title":"FLAG3D: A 3D Fitness Activity Dataset with Language Instruction","created":"2022-12-09","cited_by_count":23,"area":null},{"id":"2307.07469","title":"Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition","created":"2023-07-14","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":"2103.11770","title":"AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition","created":"2021-03-22","cited_by_count":21,"area":null},{"id":"2206.12612","title":"Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions","created":"2022-06-25","cited_by_count":21,"area":null},{"id":"2112.03328","title":"Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2021-12-06","cited_by_count":20,"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":"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":"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":"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":"2302.02327","title":"Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition","created":"2023-02-05","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":"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":"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":"2204.10312","title":"Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance","created":"2022-04-21","cited_by_count":10,"area":null},{"id":"2402.04599","title":"Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment","created":"2024-02-07","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":"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":"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":"2203.11009","title":"Continual Spatio-Temporal Graph Convolutional Networks","created":"2022-03-21","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":"2405.13206","title":"Identity-free Artificial Emotional Intelligence via Micro-Gesture Understanding","created":"2024-05-21","cited_by_count":8,"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":"2106.13391","title":"HAN: An Efficient Hierarchical Self-Attention Network for Skeleton-Based Gesture Recognition","created":"2021-06-25","cited_by_count":6,"area":null},{"id":"2111.06995","title":"A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition","created":"2021-11-13","cited_by_count":6,"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":"2506.00915","title":"3D Skeleton-Based Action Recognition: A Review","created":"2025-06-01","cited_by_count":6,"area":null},{"id":"2502.05432","title":"MoFM: A Large-Scale Human Motion Foundation Model","created":"2025-02-08","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":"2207.08095","title":"Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition","created":"2022-07-17","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":"2209.11582","title":"Pose-Aided Video-based Person Re-Identification via Recurrent Graph Convolutional Network","created":"2022-09-23","cited_by_count":4,"area":null},{"id":"2301.13360","title":"Skeleton-based Human Action Recognition via Convolutional Neural Networks (CNN)","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2403.12519","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":"2507.00566","title":"Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignment","created":"2025-07-01","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":"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":"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":"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":"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":"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":"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":"2107.14285","title":"ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation","created":"2021-07-29","cited_by_count":1,"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":"2207.05493","title":"Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network","created":"2022-07-12","cited_by_count":1,"area":null},{"id":"2208.01161","title":"Pose Uncertainty Aware Movement Synchrony Estimation via Spatial-Temporal Graph Transformer","created":"2022-08-01","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":"2306.13783","title":"Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition","created":"2023-06-23","cited_by_count":1,"area":null},{"id":"2312.15144","title":"A Generically Contrastive Spatiotemporal Representation Enhancement for 3D Skeleton Action Recognition","created":"2023-12-23","cited_by_count":1,"area":null},{"id":"2407.21525","title":"Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution","created":"2024-07-31","cited_by_count":1,"area":null},{"id":"2409.17356","title":"A vision-based framework for human behavior understanding in industrial assembly lines","created":"2024-09-25","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":"2104.05482","title":"Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2021-04-12","cited_by_count":0,"area":null},{"id":"2106.03283","title":"Video Imprint","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2207.09710","title":"Learning Sequence Representations by Non-local Recurrent Neural Memory","created":"2022-07-20","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":"2305.19343","title":"Budget-Aware Graph Convolutional Network Design using Probabilistic Magnitude Pruning","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2306.13474","title":"Efficient Online Processing with Deep Neural Networks","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2306.17590","title":"Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning","created":"2023-06-30","cited_by_count":0,"area":null},{"id":"2308.10557","title":"Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2308.16018","title":"SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition","created":"2023-08-30","cited_by_count":0,"area":null},{"id":"2312.17615","title":"One-Shot Multi-Rate Pruning of Graph Convolutional Networks","created":"2023-12-29","cited_by_count":0,"area":null},{"id":"2401.07584","title":"Collaboratively Self-supervised Video Representation Learning for Action Recognition","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2401.14034","title":"Unsupervised Spatial-Temporal Feature Enrichment and Fidelity Preservation Network for Skeleton based Action Recognition","created":"2024-01-25","cited_by_count":0,"area":null},{"id":"2410.23806","title":"Human Action Recognition (HAR) Using Skeleton-based Spatial Temporal Relative Transformer Network: ST-RTR","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2412.11813","title":"Designing Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition","created":"2024-12-16","cited_by_count":0,"area":null},{"id":"2504.02512","title":"Towards Generalizing Temporal Action Segmentation to Unseen Views","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2504.05451","title":"ViewBridge: Curriculum Knowledge Distillation for Activity View-Invariance Under Extreme Viewpoint Changes","created":"2025-04-07","cited_by_count":0,"area":"distill"},{"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}],"next_cursor":"100"}