{"total":75,"rows":[{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206,"area":"diffusion"},{"id":"2207.01567","title":"Back to MLP: A Simple Baseline for Human Motion Prediction","created":"2022-07-04","cited_by_count":100,"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":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87,"area":null},{"id":"2402.15509","title":"Seamless Human Motion Composition with Blended Positional Encodings","created":"2024-02-23","cited_by_count":80,"area":null},{"id":"2311.17057","title":"ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions","created":"2023-11-28","cited_by_count":62,"area":null},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2406.19353","title":"CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement","created":"2024-06-27","cited_by_count":44,"area":null},{"id":"2405.15763","title":"FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis","created":"2024-05-24","cited_by_count":42,"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":"2404.05218","title":"Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning","created":"2024-04-08","cited_by_count":30,"area":null},{"id":"2404.09988","title":"in2IN: Leveraging individual Information to Generate Human INteractions","created":"2024-04-15","cited_by_count":29,"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":"2306.05421","title":"Stochastic Multi-Person 3D Motion Forecasting","created":"2023-06-08","cited_by_count":28,"area":null},{"id":"2303.05095","title":"Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting","created":"2023-03-09","cited_by_count":26,"area":null},{"id":"2503.12763","title":"A Survey on Human Interaction Motion Generation","created":"2025-03-17","cited_by_count":25,"area":null},{"id":"2311.15864","title":"InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint","created":"2023-11-27","cited_by_count":23,"area":"diffusion"},{"id":"2305.12554","title":"CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion","created":"2023-05-21","cited_by_count":21,"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":"2404.11987","title":"MultiPhys: Multi-Person Physics-aware 3D Motion Estimation","created":"2024-04-18","cited_by_count":18,"area":null},{"id":"2508.01126","title":"UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation","created":"2025-08-02","cited_by_count":17,"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":"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":"2405.18839","title":"MEGA: Masked Generative Autoencoder for Human Mesh Recovery","created":"2024-05-29","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":"2503.22906","title":"SocialGen: Modeling Multi-Human Social Interaction with Language Models","created":"2025-03-28","cited_by_count":14,"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":"2208.03257","title":"3D Pose Based Feedback for Physical Exercises","created":"2022-08-05","cited_by_count":11,"area":null},{"id":"2112.00396","title":"Dyadic Human Motion Prediction","created":"2021-12-01","cited_by_count":9,"area":null},{"id":"2311.04726","title":"Social Motion Prediction with Cognitive Hierarchies","created":"2023-11-08","cited_by_count":9,"area":"offlinerl"},{"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":"2304.05758","title":"Best Practices for 2-Body Pose Forecasting","created":"2023-04-12","cited_by_count":8,"area":null},{"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":"2402.04768","title":"Robot Interaction Behavior Generation based on Social Motion Forecasting for Human-Robot Interaction","created":"2024-02-07","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":"2510.14976","title":"Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation","created":"2025-10-16","cited_by_count":7,"area":null},{"id":"2208.00774","title":"Interaction Mix and Match: Synthesizing Close Interaction using Conditional Hierarchical GAN with Multi-Hot Class Embedding","created":"2022-07-23","cited_by_count":6,"area":null},{"id":"2208.09224","title":"SoMoFormer: Social-Aware Motion Transformer for Multi-Person Motion Prediction","created":"2022-08-19","cited_by_count":6,"area":null},{"id":"2309.08947","title":"Staged Contact-Aware Global Human Motion Forecasting","created":"2023-09-16","cited_by_count":6,"area":null},{"id":"2402.19237","title":"Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting","created":"2024-02-21","cited_by_count":6,"area":null},{"id":"2405.18700","title":"Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction","created":"2024-05-29","cited_by_count":6,"area":"diffusion"},{"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":"2404.05490","title":"Two-Person Interaction Augmentation with Skeleton Priors","created":"2024-04-08","cited_by_count":5,"area":null},{"id":"2305.04443","title":"Towards Accurate Human Motion Prediction via Iterative Refinement","created":"2023-05-08","cited_by_count":4,"area":null},{"id":"2507.02565","title":"Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2512.17900","title":"Diffusion Forcing for Multi-Agent Interaction Sequence Modeling","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2306.13566","title":"The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Prediction","created":"2023-06-23","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":"2304.06411","title":"Meta-Auxiliary Learning for Adaptive Human Pose Prediction","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2506.03753","title":"HUMOF: Human Motion Forecasting in Interactive Social Scenes","created":"2025-06-04","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":"2509.23911","title":"MoReact: Generating Reactive Motion from Textual Descriptions","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2511.20446","title":"Learning to Generate Human-Human-Object Interactions from Textual Descriptions","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2306.03374","title":"PGformer: Proxy-Bridged Game Transformer for Multi-Person Highly Interactive Extreme Motion Prediction","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2310.04360","title":"SwimXYZ: A large-scale dataset of synthetic swimming motions and videos","created":"2023-10-06","cited_by_count":1,"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":"2502.08646","title":"Poly-Autoregressive Prediction for Modeling Interactions","created":"2025-02-12","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":"2512.12116","title":"Neural CDEs as Correctors for Learned Time Series Models","created":"2025-12-13","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":"2312.03528","title":"Personalized Pose Forecasting","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2404.05578","title":"Social-MAE: Social Masked Autoencoder for Multi-person Motion Representation Learning","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2411.03729","title":"Relation Learning and Aggregate-attention for Multi-person Motion Prediction","created":"2024-11-06","cited_by_count":0,"area":null},{"id":"2411.04151","title":"UnityGraph: Unified Learning of Spatio-temporal features for Multi-person Motion Prediction","created":"2024-11-06","cited_by_count":0,"area":null},{"id":"2505.12631","title":"Multi-Resolution Haar Network: Enhancing human motion prediction via Haar transform","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2512.00208","title":"ReactionMamba: Generating Short & Long Human Reaction Sequences","created":"2025-11-28","cited_by_count":0,"area":"ssm"},{"id":"2607.10408","title":"GNOCHI: Generative Neural mOdel for Close Human-Human Interactions","created":"2026-07-11","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":"2610.16624","title":"Adaptive Interaction Network for Human Motion Prediction During Human-Robot Collaboration","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}