{"total":212,"rows":[{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312,"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":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212,"area":null},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182,"area":null},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155,"area":null},{"id":"2303.14158","title":"BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects","created":"2023-03-24","cited_by_count":148,"area":null},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138,"area":null},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137,"area":null},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135,"area":null},{"id":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129,"area":null},{"id":"2212.07555","title":"IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions","created":"2022-12-14","cited_by_count":124,"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":"2209.12354","title":"InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction","created":"2022-09-26","cited_by_count":93,"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":"2207.13807","title":"Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields","created":"2022-07-27","cited_by_count":85,"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":"2303.17912","title":"CIRCLE: Capture In Rich Contextual Environments","created":"2023-03-31","cited_by_count":79,"area":null},{"id":"2212.10621","title":"Full-Body Articulated Human-Object Interaction","created":"2022-12-20","cited_by_count":78,"area":null},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76,"area":null},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74,"area":null},{"id":"2502.20390","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","created":"2025-02-27","cited_by_count":72,"area":null},{"id":"2205.07982","title":"TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement","created":"2022-05-16","cited_by_count":70,"area":null},{"id":"2212.07626","title":"NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions","created":"2022-12-15","cited_by_count":68,"area":null},{"id":"2406.17840","title":"Human-Object Interaction from Human-Level Instructions","created":"2024-06-25","cited_by_count":64,"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":"2303.16479","title":"Visibility Aware Human-Object Interaction Tracking from Single RGB Camera","created":"2023-03-29","cited_by_count":58,"area":null},{"id":"2212.04360","title":"MIME: Human-Aware 3D Scene Generation","created":"2022-12-08","cited_by_count":57,"area":null},{"id":"2401.10232","title":"ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions","created":"2024-01-18","cited_by_count":57,"area":null},{"id":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54,"area":null},{"id":"2310.03740","title":"ContactGen: Generative Contact Modeling for Grasp Generation","created":"2023-10-05","cited_by_count":53,"area":null},{"id":"2404.00299","title":"HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment","created":"2024-03-30","cited_by_count":53,"area":null},{"id":"2503.19901","title":"TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization","created":"2025-03-25","cited_by_count":51,"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":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49,"area":null},{"id":"2406.09598","title":"Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking","created":"2024-06-13","cited_by_count":48,"area":null},{"id":"2412.10523","title":"The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion","created":"2024-12-13","cited_by_count":46,"area":null},{"id":"2312.08869","title":"I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions","created":"2023-12-10","cited_by_count":44,"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":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2205.12256","title":"Differentiable Dynamics for Articulated 3d Human Motion Reconstruction","created":"2022-05-24","cited_by_count":39,"area":null},{"id":"2304.02061","title":"Generating Continual Human Motion in Diverse 3D Scenes","created":"2023-04-04","cited_by_count":39,"area":null},{"id":"2306.00777","title":"Object pop-up: Can we infer 3D objects and their poses from human interactions alone?","created":"2023-06-01","cited_by_count":37,"area":null},{"id":"2407.12371","title":"HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects","created":"2024-07-17","cited_by_count":36,"area":null},{"id":"2501.09782","title":"SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation","created":"2025-01-16","cited_by_count":32,"area":null},{"id":"2509.09555","title":"InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation","created":"2025-09-11","cited_by_count":32,"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":"2504.10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions","created":"2025-04-14","cited_by_count":31,"area":null},{"id":"2209.02485","title":"Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors","created":"2022-09-06","cited_by_count":30,"area":null},{"id":"2212.11684","title":"Scene-aware Egocentric 3D Human Pose Estimation","created":"2022-12-20","cited_by_count":30,"area":null},{"id":"2404.04819","title":"Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer","created":"2024-04-07","cited_by_count":29,"area":null},{"id":"2403.15064","title":"Recent Trends in 3D Reconstruction of General Non-Rigid Scenes","created":"2024-03-22","cited_by_count":28,"area":null},{"id":"2205.02830","title":"Interaction Replica: Tracking Human-Object Interaction and Scene Changes From Human Motion","created":"2022-05-05","cited_by_count":27,"area":null},{"id":"2303.17948","title":"CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions","created":"2023-03-31","cited_by_count":27,"area":null},{"id":"2308.11617","title":"GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistency","created":"2023-08-22","cited_by_count":27,"area":null},{"id":"2403.03122","title":"NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors","created":"2024-03-05","cited_by_count":27,"area":null},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26,"area":null},{"id":"2312.02700","title":"Revisit Human-Scene Interaction via Space Occupancy","created":"2023-12-05","cited_by_count":25,"area":null},{"id":"2412.18600","title":"ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation","created":"2024-12-24","cited_by_count":25,"area":null},{"id":"2503.12763","title":"A Survey on Human Interaction Motion Generation","created":"2025-03-17","cited_by_count":25,"area":null},{"id":"2212.00786","title":"3D Segmentation of Humans in Point Clouds with Synthetic Data","created":"2022-12-01","cited_by_count":24,"area":null},{"id":"2404.06507","title":"Reconstructing Hand-Held Objects in 3D from Images and Videos","created":"2024-04-09","cited_by_count":24,"area":null},{"id":"2407.12435","title":"F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions","created":"2024-07-17","cited_by_count":24,"area":null},{"id":"2304.03184","title":"Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream","created":"2023-04-06","cited_by_count":23,"area":null},{"id":"2308.12969","title":"ROAM: Robust and Object-Aware Motion Generation Using Neural Pose Descriptors","created":"2023-08-24","cited_by_count":23,"area":null},{"id":"2408.13953","title":"InterTrack: Tracking Human Object Interaction without Object Templates","created":"2024-08-25","cited_by_count":23,"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":"2308.14847","title":"NSF: Neural Surface Fields for Human Modeling from Monocular Depth","created":"2023-08-28","cited_by_count":21,"area":null},{"id":"2312.14024","title":"NICP: Neural ICP for 3D Human Registration at Scale","created":"2023-12-21","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":"2301.01424","title":"Scene Synthesis from Human Motion","created":"2023-01-04","cited_by_count":20,"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":"2503.13130","title":"ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation","created":"2025-03-17","cited_by_count":20,"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":"2308.12288","title":"CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images","created":"2023-08-23","cited_by_count":19,"area":null},{"id":"2403.15612","title":"InterFusion: Text-Driven Generation of 3D Human-Object Interaction","created":"2024-03-22","cited_by_count":18,"area":null},{"id":"2307.14392","title":"Human-centric Scene Understanding for 3D Large-scale Scenarios","created":"2023-07-26","cited_by_count":17,"area":null},{"id":"2403.19501","title":"RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method","created":"2024-03-28","cited_by_count":16,"area":null},{"id":"2404.04890","title":"A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2412.17730","title":"Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking","created":"2024-12-23","cited_by_count":16,"area":null},{"id":"2503.01291","title":"SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance","created":"2025-03-03","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":"2502.18373","title":"EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity","created":"2025-02-25","cited_by_count":15,"area":null},{"id":"2306.12152","title":"Exploiting Multimodal Synthetic Data for Egocentric Human-Object Interaction Detection in an Industrial Scenario","created":"2023-06-21","cited_by_count":14,"area":null},{"id":"2311.13655","title":"GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar","created":"2023-11-22","cited_by_count":14,"area":null},{"id":"2403.14937","title":"Survey on Modeling of Human-made Articulated Objects","created":"2024-03-22","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":"2412.20104","title":"SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis","created":"2024-12-28","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":"2512.11988","title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","created":"2025-12-12","cited_by_count":14,"area":null},{"id":"2310.04189","title":"Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases","created":"2023-10-06","cited_by_count":13,"area":null},{"id":"2503.15898","title":"Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions","created":"2025-03-20","cited_by_count":13,"area":null},{"id":"2505.24315","title":"InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing","created":"2025-05-30","cited_by_count":13,"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":"2503.16289","title":"SceneMI: Motion In-betweening for Modeling Human-Scene Interactions","created":"2025-03-20","cited_by_count":11,"area":null},{"id":"2401.04143","title":"RHOBIN Challenge: Reconstruction of Human Object Interaction","created":"2024-01-07","cited_by_count":10,"area":null},{"id":"2508.07863","title":"Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model","created":"2025-08-11","cited_by_count":10,"area":null},{"id":"2304.14070","title":"Compositional 3D Human-Object Neural Animation","created":"2023-04-27","cited_by_count":9,"area":null},{"id":"2407.20566","title":"Monocular Human-Object Reconstruction in the Wild","created":"2024-07-30","cited_by_count":9,"area":null},{"id":"2503.15557","title":"Motion Synthesis with Sparse and Flexible Keyjoint Control","created":"2025-03-18","cited_by_count":9,"area":null},{"id":"2506.23236","title":"VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions","created":"2025-06-29","cited_by_count":9,"area":null}],"next_cursor":"100"}