{"total":265,"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":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327,"area":null},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306,"area":null},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238,"area":null},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236,"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":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180,"area":null},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162,"area":null},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153,"area":null},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124,"area":null},{"id":"2104.14639","title":"Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation","created":"2021-04-29","cited_by_count":123,"area":null},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107,"area":null},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106,"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":"2204.08680","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","created":"2022-04-19","cited_by_count":101,"area":null},{"id":"2308.16894","title":"EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild","created":"2023-08-31","cited_by_count":97,"area":null},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95,"area":null},{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89,"area":null},{"id":"2203.09364","title":"Interacting Attention Graph for Single Image Two-Hand Reconstruction","created":"2022-03-17","cited_by_count":87,"area":null},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83,"area":null},{"id":"2207.13820","title":"Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers","created":"2022-07-27","cited_by_count":81,"area":null},{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76,"area":null},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74,"area":null},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66,"area":null},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60,"area":null},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2203.13349","title":"Occluded Human Mesh Recovery","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2212.14474","title":"Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats","created":"2022-12-29","cited_by_count":50,"area":null},{"id":"2308.11184","title":"ReFit: Recurrent Fitting Network for 3D Human Recovery","created":"2023-08-22","cited_by_count":47,"area":null},{"id":"2305.08590","title":"NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation","created":"2023-05-15","cited_by_count":45,"area":null},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45,"area":"ssm"},{"id":"2303.11726","title":"3D Human Mesh Estimation from Virtual Markers","created":"2023-03-21","cited_by_count":44,"area":null},{"id":"2308.08855","title":"Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling","created":"2023-08-17","cited_by_count":43,"area":null},{"id":"2311.17957","title":"HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting","created":"2023-11-29","cited_by_count":42,"area":"diffusion"},{"id":"2403.17934","title":"AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation","created":"2024-03-26","cited_by_count":42,"area":null},{"id":"2211.10705","title":"TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer","created":"2022-11-19","cited_by_count":41,"area":null},{"id":"2303.13796","title":"Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction","created":"2023-03-24","cited_by_count":41,"area":null},{"id":"2403.09623","title":"Score-Guided Diffusion for 3D Human Recovery","created":"2024-03-14","cited_by_count":39,"area":"diffusion"},{"id":"2303.05938","title":"ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction","created":"2023-03-10","cited_by_count":37,"area":null},{"id":"2112.07088","title":"ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses","created":"2021-12-14","cited_by_count":35,"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":"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":"2303.09187","title":"PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers","created":"2023-03-16","cited_by_count":32,"area":null},{"id":"2207.10228","title":"MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis","created":"2022-07-20","cited_by_count":31,"area":null},{"id":"2303.13357","title":"POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery","created":"2023-03-23","cited_by_count":31,"area":null},{"id":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31,"area":null},{"id":"2405.18483","title":"Towards Open Domain Text-Driven Synthesis of Multi-Person Motions","created":"2024-05-28","cited_by_count":29,"area":null},{"id":"2209.10529","title":"Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms","created":"2022-09-21","cited_by_count":28,"area":null},{"id":"2308.10123","title":"3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation","created":"2023-08-19","cited_by_count":28,"area":null},{"id":"2308.13369","title":"Distribution-Aligned Diffusion for Human Mesh Recovery","created":"2023-08-25","cited_by_count":27,"area":null},{"id":"2403.01813","title":"A Simple Baseline for Efficient Hand Mesh Reconstruction","created":"2024-03-04","cited_by_count":27,"area":null},{"id":"2304.01865","title":"SportsPose -- A Dynamic 3D sports pose dataset","created":"2023-04-04","cited_by_count":26,"area":null},{"id":"2210.07650","title":"DART: Articulated Hand Model with Diverse Accessories and Rich Textures","created":"2022-10-14","cited_by_count":25,"area":null},{"id":"2305.10329","title":"G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2308.10305","title":"Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video","created":"2023-08-20","cited_by_count":25,"area":null},{"id":"2111.04017","title":"Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation","created":"2021-11-07","cited_by_count":24,"area":null},{"id":"2304.09502","title":"Sampling is Matter: Point-guided 3D Human Mesh Reconstruction","created":"2023-04-19","cited_by_count":24,"area":null},{"id":"2311.06443","title":"CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer","created":"2023-11-11","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":"2304.03495","title":"Devil's on the Edges: Selective Quad Attention for Scene Graph Generation","created":"2023-04-07","cited_by_count":23,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2504.17695","title":"PICO: Reconstructing 3D People In Contact with Objects","created":"2025-04-24","cited_by_count":22,"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":"2206.06420","title":"GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation","created":"2022-06-13","cited_by_count":21,"area":null},{"id":"2210.01346","title":"ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Reconstruction in All Weather Conditions","created":"2022-10-04","cited_by_count":21,"area":null},{"id":"2303.04991","title":"Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation","created":"2023-03-09","cited_by_count":21,"area":null},{"id":"2308.12965","title":"POCO: 3D Pose and Shape Estimation with Confidence","created":"2023-08-24","cited_by_count":21,"area":null},{"id":"2501.08329","title":"Predicting 4D Hand Trajectory from Monocular Videos","created":"2025-01-14","cited_by_count":21,"area":null},{"id":"2504.05303","title":"InteractVLM: 3D Interaction Reasoning from 2D Foundational Models","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2409.20562","title":"SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes","created":"2024-09-30","cited_by_count":20,"area":null},{"id":"2302.07408","title":"Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation","created":"2023-02-15","cited_by_count":19,"area":null},{"id":"2303.16456","title":"Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation","created":"2023-03-29","cited_by_count":19,"area":null},{"id":"2305.12497","title":"PanoContext-Former: Panoramic Total Scene Understanding with a Transformer","created":"2023-05-21","cited_by_count":19,"area":null},{"id":"2211.11734","title":"PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation","created":"2022-11-21","cited_by_count":18,"area":null},{"id":"2303.12564","title":"RaBit: Parametric Modeling of 3D Biped Cartoon Characters with a Topological-consistent Dataset","created":"2023-03-22","cited_by_count":18,"area":null},{"id":"2308.14082","title":"Reconstructing Interacting Hands with Interaction Prior from Monocular Images","created":"2023-08-27","cited_by_count":18,"area":null},{"id":"2112.03258","title":"DoodleFormer: Creative Sketch Drawing with Transformers","created":"2021-12-06","cited_by_count":17,"area":null},{"id":"2210.06270","title":"Event-based Non-Rigid Reconstruction from Contours","created":"2022-10-12","cited_by_count":17,"area":null},{"id":"2407.11174","title":"iHuman: Instant Animatable Digital Humans From Monocular Videos","created":"2024-07-15","cited_by_count":17,"area":null},{"id":"2208.11251","title":"Learnable human mesh triangulation for 3D human pose and shape estimation","created":"2022-08-24","cited_by_count":16,"area":null},{"id":"2305.01618","title":"ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation","created":"2023-05-02","cited_by_count":16,"area":null},{"id":"2308.04808","title":"Joint-Relation Transformer for Multi-Person Motion Prediction","created":"2023-08-09","cited_by_count":16,"area":null},{"id":"2309.09301","title":"RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimation","created":"2023-09-17","cited_by_count":16,"area":null},{"id":"2403.03270","title":"Bi-KVIL: Keypoints-based Visual Imitation Learning of Bimanual Manipulation Tasks","created":"2024-03-05","cited_by_count":16,"area":"offlinerl"},{"id":"2411.19824","title":"SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens","created":"2024-11-29","cited_by_count":16,"area":null},{"id":"2208.10211","title":"PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling","created":"2022-08-22","cited_by_count":15,"area":null},{"id":"2208.10652","title":"Learning Visibility for Robust Dense Human Body Estimation","created":"2022-08-23","cited_by_count":15,"area":null},{"id":"2303.16874","title":"CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network","created":"2023-03-29","cited_by_count":15,"area":null},{"id":"2304.03635","title":"A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2023-04-07","cited_by_count":15,"area":null},{"id":"2409.04033","title":"Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamics","created":"2024-09-06","cited_by_count":15,"area":null},{"id":"2403.07346","title":"Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction","created":"2024-03-12","cited_by_count":14,"area":null},{"id":"2405.18839","title":"MEGA: Masked Generative Autoencoder for Human Mesh Recovery","created":"2024-05-29","cited_by_count":14,"area":null},{"id":"2406.01334","title":"HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models","created":"2024-06-03","cited_by_count":14,"area":"diffusion"},{"id":"2502.16533","title":"A Survey of Graph Transformers: Architectures, Theories and Applications","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2505.11152","title":"Learning Dense Hand Contact Estimation from Imbalanced Data","created":"2025-05-16","cited_by_count":14,"area":null},{"id":"2306.03847","title":"Learning Human Mesh Recovery in 3D Scenes","created":"2023-06-06","cited_by_count":13,"area":null},{"id":"2312.08291","title":"VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space","created":"2023-12-13","cited_by_count":13,"area":null},{"id":"2403.18575","title":"HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions","created":"2024-03-27","cited_by_count":13,"area":null}],"next_cursor":"100"}