{"total":20,"rows":[{"id":"2504.17695","title":"PICO: Reconstructing 3D People In Contact with Objects","created":"2025-04-24","cited_by_count":22,"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":"2512.00960","title":"Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction","created":"2025-11-30","cited_by_count":3,"area":null},{"id":"2510.23203","title":"DecoDINO: 3D Human-Scene Contact Prediction with Semantic Classification","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2602.19679","title":"TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.02329","title":"HAMMER: Harnessing MLLM via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.14435","title":"End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2604.19923","title":"UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2604.20841","title":"DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2508.21795","title":"TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2512.14696","title":"CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2604.12923","title":"Pi-HOC: Pairwise 3D Human-Object Contact Estimation","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.20800","title":"LEXIS: LatEnt ProXimal Interaction Signatures for 3D HOI from an Image","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.14462","title":"Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.17014","title":"RHINO: Reconstructing Human Interactions with Novel Objects from Monocular Videos","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.05359","title":"Recovering Physically Plausible Human-Object Interactions from Monocular Videos","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2608.28386","title":"GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.32551","title":"Harnessing Coupled Stream Completion For Human-Object Interaction Modeling","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.00451","title":"PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01210","title":"EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}