{"total":102,"rows":[{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257,"area":null},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200,"area":null},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193,"area":null},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142,"area":null},{"id":"2505.03729","title":"Visual Imitation Enables Contextual Humanoid Control","created":"2025-05-06","cited_by_count":68,"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":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2107.07797","title":"Conditional Directed Graph Convolution for 3D Human Pose Estimation","created":"2021-07-16","cited_by_count":52,"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":"2109.07531","title":"Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers","created":"2021-09-15","cited_by_count":46,"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":"2105.06152","title":"When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks","created":"2021-05-13","cited_by_count":41,"area":null},{"id":"2104.11452","title":"SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos","created":"2021-04-23","cited_by_count":40,"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":"2210.06110","title":"Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers","created":"2022-10-12","cited_by_count":33,"area":null},{"id":"2104.02710","title":"The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions","created":"2021-04-06","cited_by_count":31,"area":null},{"id":"2104.13502","title":"KAMA: 3D Keypoint Aware Body Mesh Articulation","created":"2021-04-27","cited_by_count":27,"area":null},{"id":"2210.07886","title":"PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning","created":"2022-10-14","cited_by_count":23,"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":"2308.13872","title":"Vision-Based Human Pose Estimation via Deep Learning: A Survey","created":"2023-08-26","cited_by_count":20,"area":null},{"id":"2108.13958","title":"A Novel Dataset for Keypoint Detection of quadruped Animals from Images","created":"2021-08-31","cited_by_count":19,"area":null},{"id":"2101.10808","title":"Fast Facial Landmark Detection and Applications: A Survey","created":"2021-01-12","cited_by_count":18,"area":null},{"id":"2406.13987","title":"Image anomaly detection and prediction scheme based on SSA optimized ResNet50-BiGRU model","created":"2024-06-20","cited_by_count":18,"area":null},{"id":"2104.10609","title":"Lifting Monocular Events to 3D Human Poses","created":"2021-04-21","cited_by_count":16,"area":null},{"id":"2104.03100","title":"HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap","created":"2021-04-07","cited_by_count":15,"area":null},{"id":"2111.02360","title":"Subpixel Heatmap Regression for Facial Landmark Localization","created":"2021-11-03","cited_by_count":14,"area":null},{"id":"2308.01854","title":"Reconstructing Three-Dimensional Models of Interacting Humans","created":"2023-08-03","cited_by_count":14,"area":null},{"id":"2405.17698","title":"BaboonLand Dataset: Tracking Primates in the Wild and Automating Behaviour Recognition from Drone Videos","created":"2024-05-27","cited_by_count":14,"area":null},{"id":"2101.08967","title":"Human Interaction Recognition Framework based on Interacting Body Part Attention","created":"2021-01-22","cited_by_count":11,"area":null},{"id":"2110.08825","title":"Localization with Sampling-Argmax","created":"2021-10-17","cited_by_count":11,"area":null},{"id":"2109.09166","title":"Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition","created":"2021-09-19","cited_by_count":9,"area":null},{"id":"2111.13285","title":"3D Pose Estimation and Future Motion Prediction from 2D Images","created":"2021-11-26","cited_by_count":8,"area":null},{"id":"2204.06818","title":"Interpretable Vertebral Fracture Quantification via Anchor-Free Landmarks Localization","created":"2022-04-14","cited_by_count":8,"area":null},{"id":"2307.09026","title":"ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting","created":"2023-07-18","cited_by_count":8,"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":"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":"2103.03170","title":"Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions","created":"2021-03-04","cited_by_count":6,"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":"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":"2203.10554","title":"3D Human Pose Estimation Using M\\\"obius Graph Convolutional Networks","created":"2022-03-20","cited_by_count":6,"area":null},{"id":"2301.02979","title":"CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations","created":"2023-01-08","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":"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":"2404.10880","title":"HumMUSS: Human Motion Understanding using State Space Models","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2106.14706","title":"Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos","created":"2021-06-28","cited_by_count":5,"area":null},{"id":"2109.14306","title":"Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2110.08814","title":"TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding","created":"2021-10-17","cited_by_count":5,"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":"2305.13765","title":"Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2102.07355","title":"Win-Fail Action Recognition","created":"2021-02-15","cited_by_count":4,"area":null},{"id":"2204.11548","title":"PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation","created":"2022-04-25","cited_by_count":4,"area":null},{"id":"2312.06797","title":"Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2401.15236","title":"Adaptive Deep Learning for Efficient Visual Pose Estimation aboard Ultra-low-power Nano-drones","created":"2024-01-26","cited_by_count":4,"area":null},{"id":"2406.19290","title":"Human Modelling and Pose Estimation Overview","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2505.13140","title":"CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flow","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2112.12074","title":"Spatio-Temporal CNN baseline method for the Sports Video Task of MediaEval 2021 benchmark","created":"2021-12-16","cited_by_count":3,"area":null},{"id":"2303.01931","title":"Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs","created":"2023-03-03","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":"2405.17397","title":"Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2501.10098","title":"landmarker: a Toolkit for Anatomical Landmark Localization in 2D/3D Images","created":"2025-01-17","cited_by_count":3,"area":null},{"id":"2502.09460","title":"Metamorphic Testing for Pose Estimation Systems","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2503.14106","title":"Reliable uncertainty quantification for 2D/3D anatomical landmark localization using multi-output conformal prediction","created":"2025-03-18","cited_by_count":3,"area":null},{"id":"2508.10897","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2207.06828","title":"Pose-based Tremor Classification for Parkinson's Disease Diagnosis from Video","created":"2022-07-14","cited_by_count":2,"area":null},{"id":"2311.16477","title":"UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning","created":"2023-11-24","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":"2106.04269","title":"HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation","created":"2021-06-08","cited_by_count":1,"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":"2110.13598","title":"Incremental Learning for Animal Pose Estimation using RBF k-DPP","created":"2021-10-26","cited_by_count":1,"area":null},{"id":"2111.06762","title":"Diversity-Promoting Human Motion Interpolation via Conditional Variational Auto-Encoder","created":"2021-11-12","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":"2210.08562","title":"A New Spatio-Temporal Loss Function for 3D Motion Reconstruction and Extended Temporal Metrics for Motion Evaluation","created":"2022-10-16","cited_by_count":1,"area":null},{"id":"2402.13955","title":"BEE-NET: A deep neural network to identify in-the-wild Bodily Expression of Emotions","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2403.06577","title":"Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition","created":"2024-03-11","cited_by_count":1,"area":null},{"id":"2407.10220","title":"PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2409.11104","title":"Depth-based Privileged Information for Boosting 3D Human Pose Estimation on RGB","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2409.18561","title":"AL-GTD: Deep Active Learning for Gaze Target Detection","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2510.19078","title":"UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2602.19874","title":"BigMaQ: A Big Macaque Motion and Animation Dataset Bridging Image and 3D Pose Representations","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2608.00371","title":"Decoding Children's Gait Behavior","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2101.06702","title":"Deep Learning based Virtual Point Tracking for Real-Time Target-less Dynamic Displacement Measurement in Railway Applications","created":"2021-01-17","cited_by_count":0,"area":null},{"id":"2104.00953","title":"Learning Transferable Kinematic Dictionary for 3D Human Pose and Shape Reconstruction","created":"2021-04-02","cited_by_count":0,"area":null},{"id":"2112.01736","title":"Gesture Recognition with a Skeleton-Based Keyframe Selection Module","created":"2021-12-03","cited_by_count":0,"area":null},{"id":"2204.08671","title":"ActAR: Actor-Driven Pose Embeddings for Video Action Recognition","created":"2022-04-19","cited_by_count":0,"area":null},{"id":"2204.13492","title":"Representation Recycling for Streaming Video Analysis","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2204.13548","title":"Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2204.13678","title":"Unified Simulation, Perception, and Generation of Human Behavior","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2206.06430","title":"A Training Method For VideoPose3D With Ideology of Action Recognition","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2212.01353","title":"Video-based Pose-Estimation Data as Source for Transfer Learning in Human Activity Recognition","created":"2022-12-02","cited_by_count":0,"area":null},{"id":"2303.12728","title":"LocalEyenet: Deep Attention framework for Localization of Eyes","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2304.07072","title":"CornerFormer: Boosting Corner Representation for Fine-Grained Structured Reconstruction","created":"2023-04-14","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":"2312.01713","title":"Disentangled Interaction Representation for One-Stage Human-Object Interaction Detection","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2404.09499","title":"Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignment","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2409.00449","title":"LangPose: Language-Aligned Motion for Robust 3D Human Pose Estimation","created":"2024-08-31","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":"2510.19475","title":"PRGCN: A Graph Memory Network for Cross-Sequence Pattern Reuse in 3D Human Pose Estimation","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2512.12549","title":"Supervised Contrastive Frame Aggregation for Video Representation Learning","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2603.08540","title":"PCFEx: Point Cloud Feature Extraction for Graph Neural Networks","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.22830","title":"2D Pre-Training for 3D Pose Estimation","created":"2026-04-19","cited_by_count":0,"area":null}],"next_cursor":"100"}