{"total":329,"rows":[{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350,"area":null},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272,"area":null},{"id":"2101.11939","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","created":"2021-01-28","cited_by_count":242,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"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":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131,"area":null},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112,"area":null},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107,"area":null},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103,"area":null},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96,"area":null},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"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":"2303.11579","title":"Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation","created":"2023-03-21","cited_by_count":82,"area":null},{"id":"2203.07628","title":"P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation","created":"2022-03-15","cited_by_count":80,"area":null},{"id":"2107.03332","title":"SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation","created":"2021-07-07","cited_by_count":68,"area":null},{"id":"2112.02466","title":"Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer","created":"2021-12-05","cited_by_count":68,"area":null},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65,"area":null},{"id":"2204.07855","title":"Towards a Deeper Understanding of Skeleton-based Gait Recognition","created":"2022-04-16","cited_by_count":56,"area":null},{"id":"2103.02440","title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","created":"2021-03-03","cited_by_count":55,"area":null},{"id":"2202.08471","title":"TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline","created":"2022-02-17","cited_by_count":55,"area":null},{"id":"2102.09546","title":"Deep Gait Recognition: A Survey","created":"2021-02-18","cited_by_count":54,"area":null},{"id":"2108.12630","title":"GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer","created":"2021-08-28","cited_by_count":54,"area":null},{"id":"2103.07254","title":"Deep Dual Consecutive Network for Human Pose Estimation","created":"2021-03-12","cited_by_count":51,"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":"2103.07854","title":"Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis","created":"2021-03-14","cited_by_count":46,"area":null},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","cited_by_count":42,"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":"2308.07092","title":"Masked Motion Predictors are Strong 3D Action Representation Learners","created":"2023-08-14","cited_by_count":41,"area":null},{"id":"2103.02184","title":"RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Images","created":"2021-03-03","cited_by_count":39,"area":null},{"id":"2207.10955","title":"Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection","created":"2022-07-22","cited_by_count":39,"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":"2106.03772","title":"Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking","created":"2021-06-07","cited_by_count":37,"area":null},{"id":"2303.12337","title":"Music-Driven Group Choreography","created":"2023-03-22","cited_by_count":37,"area":null},{"id":"2201.03746","title":"TSA-Net: Tube Self-Attention Network for Action Quality Assessment","created":"2022-01-11","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":"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":"2105.14185","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","created":"2021-05-29","cited_by_count":34,"area":null},{"id":"2206.14674","title":"Signature Methods in Machine Learning","created":"2022-06-29","cited_by_count":34,"area":null},{"id":"2207.14192","title":"Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection","created":"2022-07-28","cited_by_count":34,"area":null},{"id":"2108.10378","title":"Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras","created":"2021-08-23","cited_by_count":33,"area":null},{"id":"2112.11593","title":"AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation","created":"2021-12-22","cited_by_count":32,"area":null},{"id":"2304.01199","title":"On the Benefits of 3D Pose and Tracking for Human Action Recognition","created":"2023-04-03","cited_by_count":32,"area":null},{"id":"2103.04570","title":"Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing","created":"2021-03-08","cited_by_count":31,"area":null},{"id":"2203.14065","title":"Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capture","created":"2022-03-26","cited_by_count":31,"area":null},{"id":"2312.12664","title":"UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection","created":"2023-12-19","cited_by_count":31,"area":null},{"id":"2101.09866","title":"Supervision by Registration and Triangulation for Landmark Detection","created":"2021-01-25","cited_by_count":30,"area":null},{"id":"2101.11223","title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","created":"2021-01-27","cited_by_count":30,"area":null},{"id":"2108.08844","title":"Gravity-Aware Monocular 3D Human-Object Reconstruction","created":"2021-08-19","cited_by_count":30,"area":null},{"id":"2110.07235","title":"HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media","created":"2021-10-14","cited_by_count":29,"area":null},{"id":"2110.13408","title":"Learning Rich Features for Gait Recognition by Integrating Skeletons and Silhouettes","created":"2021-10-26","cited_by_count":29,"area":null},{"id":"2105.09803","title":"Weakly-Supervised Physically Unconstrained Gaze Estimation","created":"2021-05-20","cited_by_count":28,"area":null},{"id":"2112.04294","title":"A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos","created":"2021-12-08","cited_by_count":28,"area":null},{"id":"2202.06851","title":"HAKE: A Knowledge Engine Foundation for Human Activity Understanding","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2112.06183","title":"Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species","created":"2021-12-12","cited_by_count":27,"area":null},{"id":"2104.11712","title":"Skeletor: Skeletal Transformers for Robust Body-Pose Estimation","created":"2021-04-23","cited_by_count":26,"area":null},{"id":"2110.10355","title":"Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras","created":"2021-10-20","cited_by_count":26,"area":null},{"id":"2308.07313","title":"Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation","created":"2023-08-14","cited_by_count":26,"area":null},{"id":"2206.04511","title":"Efficient Human Pose Estimation via 3D Event Point Cloud","created":"2022-06-09","cited_by_count":25,"area":null},{"id":"2206.11752","title":"CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose","created":"2022-06-23","cited_by_count":25,"area":null},{"id":"2110.02330","title":"Shape-aware Multi-Person Pose Estimation from Multi-View Images","created":"2021-10-05","cited_by_count":24,"area":null},{"id":"2203.15227","title":"Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation","created":"2022-03-29","cited_by_count":24,"area":null},{"id":"2205.02301","title":"BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking","created":"2022-05-04","cited_by_count":24,"area":null},{"id":"2208.11547","title":"ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild","created":"2022-08-23","cited_by_count":23,"area":null},{"id":"2111.07868","title":"Tracking People with 3D Representations","created":"2021-11-15","cited_by_count":22,"area":null},{"id":"2112.03649","title":"Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection","created":"2021-12-07","cited_by_count":22,"area":null},{"id":"2208.10414","title":"MetaFi: Device-Free Pose Estimation via Commodity WiFi for Metaverse Avatar Simulation","created":"2022-08-22","cited_by_count":22,"area":null},{"id":"2209.00065","title":"ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting","created":"2022-08-31","cited_by_count":22,"area":null},{"id":"2312.14404","title":"Cross-Covariate Gait Recognition: A Benchmark","created":"2023-12-22","cited_by_count":22,"area":null},{"id":"2403.14497","title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","created":"2024-03-21","cited_by_count":22,"area":null},{"id":"2109.09903","title":"AirDOS: Dynamic SLAM benefits from Articulated Objects","created":"2021-09-21","cited_by_count":21,"area":null},{"id":"2111.12696","title":"A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose","created":"2021-11-24","cited_by_count":21,"area":null},{"id":"2204.07370","title":"2D Human Pose Estimation: A Survey","created":"2022-04-15","cited_by_count":21,"area":null},{"id":"2303.15167","title":"Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features","created":"2023-03-27","cited_by_count":21,"area":null},{"id":"2404.02041","title":"SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation","created":"2024-04-02","cited_by_count":21,"area":null},{"id":"2105.11731","title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","created":"2021-05-25","cited_by_count":20,"area":null},{"id":"2109.10498","title":"Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification","created":"2021-09-22","cited_by_count":20,"area":null},{"id":"2111.08557","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","created":"2021-11-16","cited_by_count":20,"area":null},{"id":"2212.07010","title":"Cross-Domain Video Anomaly Detection without Target Domain Adaptation","created":"2022-12-14","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":"2105.13965","title":"Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation","created":"2021-05-28","cited_by_count":19,"area":null},{"id":"2301.05175","title":"Scene-Aware 3D Multi-Human Motion Capture from a Single Camera","created":"2023-01-12","cited_by_count":19,"area":null},{"id":"2104.00287","title":"Learning to Track Instances without Video Annotations","created":"2021-04-01","cited_by_count":18,"area":null},{"id":"2110.05132","title":"The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation","created":"2021-10-11","cited_by_count":18,"area":null},{"id":"2110.07495","title":"Simple Baseline for Single Human Motion Forecasting","created":"2021-10-14","cited_by_count":18,"area":null},{"id":"2308.15844","title":"Reconstructing Groups of People with Hypergraph Relational Reasoning","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2205.10636","title":"AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints","created":"2022-05-21","cited_by_count":17,"area":null},{"id":"2303.08475","title":"Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2205.01271","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","created":"2022-05-03","cited_by_count":16,"area":null},{"id":"2112.04477","title":"Tracking People by Predicting 3D Appearance, Location & Pose","created":"2021-12-08","cited_by_count":15,"area":null},{"id":"2207.05375","title":"Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior","created":"2022-07-12","cited_by_count":15,"area":null},{"id":"2104.11216","title":"Hierarchical Motion Understanding via Motion Programs","created":"2021-04-22","cited_by_count":14,"area":null},{"id":"2109.03622","title":"Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation","created":"2021-09-08","cited_by_count":14,"area":null},{"id":"2201.08613","title":"Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization","created":"2022-01-21","cited_by_count":14,"area":null},{"id":"2207.03714","title":"Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation","created":"2022-07-08","cited_by_count":14,"area":null},{"id":"2301.00114","title":"Skeletal Video Anomaly Detection using Deep Learning: Survey, Challenges and Future Directions","created":"2022-12-31","cited_by_count":14,"area":null},{"id":"2301.09489","title":"Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection","created":"2023-01-23","cited_by_count":14,"area":null},{"id":"2107.08982","title":"InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimation","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2201.10175","title":"RFMask: A Simple Baseline for Human Silhouette Segmentation with Radio Signals","created":"2022-01-25","cited_by_count":13,"area":null}],"next_cursor":"100"}