{"total":87,"rows":[{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98,"area":null},{"id":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78,"area":null},{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76,"area":null},{"id":"2602.15989","title":"SAM 3D Body: Robust Full-Body Human Mesh Recovery","created":"2026-02-17","cited_by_count":69,"area":null},{"id":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68,"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":"2306.09337","title":"Generative Proxemics: A Prior for 3D Social Interaction from Images","created":"2023-06-15","cited_by_count":43,"area":"diffusion"},{"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":"2503.01610","title":"Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior","created":"2025-03-03","cited_by_count":31,"area":null},{"id":"2502.20370","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation","created":"2025-02-27","cited_by_count":28,"area":null},{"id":"2503.12763","title":"A Survey on Human Interaction Motion Generation","created":"2025-03-17","cited_by_count":25,"area":null},{"id":"2412.06334","title":"TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions","created":"2024-12-09","cited_by_count":20,"area":null},{"id":"2404.11291","title":"Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption","created":"2024-04-17","cited_by_count":19,"area":"diffusion"},{"id":"2403.16080","title":"PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling","created":"2024-03-24","cited_by_count":18,"area":null},{"id":"2404.14410","title":"Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses","created":"2024-04-22","cited_by_count":17,"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":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15,"area":null},{"id":"2308.01854","title":"Reconstructing Three-Dimensional Models of Interacting Humans","created":"2023-08-03","cited_by_count":14,"area":null},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2501.02771","title":"WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation","created":"2025-01-06","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":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2607.09024","title":"Video Generation Models are General-Purpose Vision Learners","created":"2026-07-10","cited_by_count":14,"area":null},{"id":"2505.18078","title":"DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2306.07399","title":"4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements","created":"2023-06-12","cited_by_count":12,"area":null},{"id":"2406.01595","title":"MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild","created":"2024-06-03","cited_by_count":12,"area":null},{"id":"2508.15767","title":"ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling","created":"2025-08-21","cited_by_count":12,"area":null},{"id":"2507.15365","title":"DAViD: Data-efficient and Accurate Vision Models from Synthetic Data","created":"2025-07-21","cited_by_count":11,"area":null},{"id":"2602.12370","title":"LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens","created":"2026-02-12","cited_by_count":11,"area":null},{"id":"2511.03589","title":"Human Mesh Modeling for Anny Body","created":"2025-11-05","cited_by_count":10,"area":null},{"id":"2409.04440","title":"Synergy and Synchrony in Couple Dances","created":"2024-09-06","cited_by_count":9,"area":null},{"id":"2505.01838","title":"MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitization","created":"2025-05-03","cited_by_count":9,"area":null},{"id":"2511.15586","title":"MHR: Momentum Human Rig","created":"2025-11-19","cited_by_count":9,"area":null},{"id":"2602.01661","title":"From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2403.11111","title":"Diffusion Models are Efficient Data Generators for Human Mesh Recovery","created":"2024-03-17","cited_by_count":8,"area":"diffusion"},{"id":"2508.04681","title":"Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions","created":"2025-08-06","cited_by_count":8,"area":null},{"id":"2312.09641","title":"Ins-HOI: Instance Aware Human-Object Interactions Recovery","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2405.11690","title":"InterAct: Capture and Modelling of Realistic, Expressive and Interactive Activities between Two Persons in Daily Scenarios","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2408.02110","title":"AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos","created":"2024-08-04","cited_by_count":7,"area":null},{"id":"2503.13120","title":"3D Human Interaction Generation: A Survey","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2505.10250","title":"ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization","created":"2025-05-15","cited_by_count":7,"area":null},{"id":"2510.14976","title":"Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation","created":"2025-10-16","cited_by_count":7,"area":null},{"id":"2405.03689","title":"Pose Priors from Language Models","created":"2024-05-06","cited_by_count":6,"area":null},{"id":"2512.19692","title":"Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models","created":"2025-12-22","cited_by_count":6,"area":"diffusion"},{"id":"2409.18364","title":"Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images","created":"2024-09-27","cited_by_count":5,"area":"diffusion"},{"id":"2412.13058","title":"CondiMen: Conditional Multi-Person Mesh Recovery","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2603.25892","title":"THFM: A Unified Video Foundation Model for 4D Human Perception and Beyond","created":"2026-03-26","cited_by_count":5,"area":"diffusion"},{"id":"2507.02565","title":"Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2605.05207","title":"Syn4D: A Multiview Synthetic 4D Dataset","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2401.17212","title":"ContactGen: Contact-Guided Interactive 3D Human Generation for Partners","created":"2024-01-30","cited_by_count":3,"area":"diffusion"},{"id":"2407.02165","title":"WildAvatar: Learning In-the-wild 3D Avatars from the Web","created":"2024-07-02","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":"2506.06645","title":"Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modeling","created":"2025-06-07","cited_by_count":3,"area":null},{"id":"2511.13282","title":"Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2402.16806","title":"Multi-Human Mesh Recovery with Transformers","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2502.13968","title":"Betsu-Betsu: Multi-View Separable 3D Reconstruction of Two Interacting Objects","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2504.03602","title":"Robust Human Registration with Body Part Segmentation on Noisy Point Clouds","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2507.19684","title":"CoMPAS3D: A Dataset and Benchmark for Interactive Motion","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2509.05747","title":"InterAct: A Large-Scale Dataset of Dynamic, Expressive and Interactive Activities between Two People in Daily Scenarios","created":"2025-09-06","cited_by_count":2,"area":null},{"id":"2509.23393","title":"Generative Modeling of Shape-Dependent Self-Contact Human Poses","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2602.19180","title":"VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery","created":"2026-02-22","cited_by_count":2,"area":"alignment"},{"id":"2604.21926","title":"Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2606.14841","title":"Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2410.00309","title":"Ask, Pose, Unite: Scaling Data Acquisition for Close Interactions with Vision Language Models","created":"2024-10-01","cited_by_count":1,"area":"mllm"},{"id":"2504.08175","title":"Multi-person Physics-based Pose Estimation for Combat Sports","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2509.10096","title":"HHI-Assist: A Dataset and Benchmark of Human-Human Interaction in Physical Assistance Scenario","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2510.15786","title":"DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2511.22184","title":"Shoe Style-Invariant and Ground-Aware Learning for Dense Foot Contact Estimation","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2603.15083","title":"ReactMotion: Generating Reactive Listener Motions from Speaker Utterance","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.28064","title":"\\textit{4DSurf}: High-Fidelity Dynamic Scene Surface Reconstruction","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2605.04728","title":"Anny-Fit: All-Age Human Mesh Recovery","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.05886","title":"Training-Free Dense Hand Contact Estimation with Multi-Modal Large Language Models","created":"2026-05-07","cited_by_count":1,"area":"mllm"},{"id":"2606.20542","title":"CalTennis: Large Multi-View Tennis Video Dataset and Benchmark of Monocular-to-3D Pose Estimation","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2609.01899","title":"TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2506.13040","title":"MAMMA: Markerless & Automatic Multi-Person Motion Action Capture","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2507.07519","title":"MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2603.08147","title":"MV-Fashion: Towards Enabling Virtual Try-On and Size Estimation with Multi-View Paired Data","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.00857","title":"Sparkle: A Robust and Versatile Representation for Point Cloud based Human Motion Capture","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.05436","title":"Human Interaction-Aware 3D Reconstruction from a Single Image","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.13581","title":"SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.04554","title":"InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2607.10408","title":"GNOCHI: Generative Neural mOdel for Close Human-Human Interactions","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.17342","title":"STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.20312","title":"Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.32454","title":"De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shift","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36937","title":"WeLike2Party! In-Context Motion Transfer for Multi-Human Image Animation","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}