{"total":71,"rows":[{"id":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324,"area":null},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249,"area":null},{"id":"2109.00179","title":"Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds","created":"2021-09-01","cited_by_count":180,"area":null},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158,"area":null},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133,"area":null},{"id":"2204.02445","title":"CHORE: Contact, Human and Object REconstruction from a single RGB image","created":"2022-04-05","cited_by_count":95,"area":null},{"id":"2103.06422","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","created":"2021-03-11","cited_by_count":94,"area":null},{"id":"2403.18036","title":"Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance","created":"2024-03-26","cited_by_count":80,"area":"diffusion"},{"id":"2212.10621","title":"Full-Body Articulated Human-Object Interaction","created":"2022-12-20","cited_by_count":78,"area":null},{"id":"2404.03421","title":"Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View","created":"2024-04-04","cited_by_count":61,"area":null},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56,"area":null},{"id":"2310.03740","title":"ContactGen: Generative Contact Modeling for Grasp Generation","created":"2023-10-05","cited_by_count":53,"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":"2404.16666","title":"PhyRecon: Physically Plausible Neural Scene Reconstruction","created":"2024-04-25","cited_by_count":45,"area":null},{"id":"2207.08656","title":"Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes","created":"2022-07-18","cited_by_count":44,"area":null},{"id":"2103.14230","title":"Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution","created":"2021-03-26","cited_by_count":43,"area":null},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2108.08420","title":"D3D-HOI: Dynamic 3D Human-Object Interactions from Videos","created":"2021-08-19","cited_by_count":39,"area":null},{"id":"2203.17251","title":"Continuous Scene Representations for Embodied AI","created":"2022-03-31","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":"2311.00457","title":"Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture","created":"2023-11-01","cited_by_count":37,"area":null},{"id":"2202.13519","title":"PartAfford: Part-level Affordance Discovery from 3D Objects","created":"2022-02-28","cited_by_count":36,"area":null},{"id":"2108.10743","title":"DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization","created":"2021-08-24","cited_by_count":33,"area":null},{"id":"2401.12978","title":"Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models","created":"2024-01-23","cited_by_count":32,"area":"diffusion"},{"id":"2403.12835","title":"AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents","created":"2024-03-19","cited_by_count":32,"area":"offlinerl"},{"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":"2109.05566","title":"PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds","created":"2021-09-12","cited_by_count":26,"area":null},{"id":"2111.00312","title":"3DP3: 3D Scene Perception via Probabilistic Programming","created":"2021-10-30","cited_by_count":26,"area":null},{"id":"2203.11471","title":"Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization","created":"2022-03-22","cited_by_count":25,"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":"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":"2503.22420","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","created":"2025-03-28","cited_by_count":23,"area":null},{"id":"2111.12608","title":"Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing","created":"2021-11-24","cited_by_count":22,"area":null},{"id":"2301.01424","title":"Scene Synthesis from Human Motion","created":"2023-01-04","cited_by_count":20,"area":null},{"id":"2103.07969","title":"Monte Carlo Scene Search for 3D Scene Understanding","created":"2021-03-14","cited_by_count":19,"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":"2305.12497","title":"PanoContext-Former: Panoramic Total Scene Understanding with a Transformer","created":"2023-05-21","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":"2203.11130","title":"PACS: A Dataset for Physical Audiovisual CommonSense Reasoning","created":"2022-03-21","cited_by_count":18,"area":"lr"},{"id":"2207.04364","title":"Sequential Manipulation Planning on Scene Graph","created":"2022-07-10","cited_by_count":17,"area":null},{"id":"2103.16095","title":"Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments","created":"2021-03-30","cited_by_count":15,"area":null},{"id":"2510.11649","title":"PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image","created":"2025-10-13","cited_by_count":14,"area":null},{"id":"2310.19559","title":"Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2023-10-30","cited_by_count":13,"area":"lr"},{"id":"2204.07061","title":"Egocentric Human-Object Interaction Detection Exploiting Synthetic Data","created":"2022-04-14","cited_by_count":11,"area":null},{"id":"2207.14268","title":"MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud","created":"2022-07-28","cited_by_count":11,"area":null},{"id":"2210.02075","title":"On the Learning Mechanisms in Physical Reasoning","created":"2022-10-05","cited_by_count":11,"area":null},{"id":"2303.09410","title":"Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning","created":"2023-03-16","cited_by_count":10,"area":null},{"id":"2304.08492","title":"STRAP: Structured Object Affordance Segmentation with Point Supervision","created":"2023-04-17","cited_by_count":10,"area":null},{"id":"2405.12460","title":"Physics-based Scene Layout Generation from Human Motion","created":"2024-05-21","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":"2509.07920","title":"ScoreHOI: Physically Plausible Reconstruction of Human-Object Interaction via Score-Guided Diffusion","created":"2025-09-09","cited_by_count":9,"area":"diffusion"},{"id":"2510.16714","title":"SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes","created":"2025-10-19","cited_by_count":8,"area":"lr"},{"id":"2103.01403","title":"A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics","created":"2021-03-02","cited_by_count":6,"area":null},{"id":"2303.05676","title":"Rearrange Indoor Scenes for Human-Robot Co-Activity","created":"2023-03-10","cited_by_count":5,"area":null},{"id":"2407.20545","title":"StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset","created":"2024-07-30","cited_by_count":5,"area":null},{"id":"2207.03204","title":"MCTS with Refinement for Proposals Selection Games in Scene Understanding","created":"2022-07-07","cited_by_count":4,"area":null},{"id":"2212.01186","title":"A General Purpose Supervisory Signal for Embodied Agents","created":"2022-12-01","cited_by_count":3,"area":null},{"id":"2307.14570","title":"Physically Plausible 3D Human-Scene Reconstruction from Monocular RGB Image using an Adversarial Learning Approach","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2309.03542","title":"Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction","created":"2023-09-07","cited_by_count":2,"area":null},{"id":"2111.12924","title":"Joint stereo 3D object detection and implicit surface reconstruction","created":"2021-11-25","cited_by_count":1,"area":null},{"id":"2306.05846","title":"Motion-DVAE: Unsupervised learning for fast human motion denoising","created":"2023-06-09","cited_by_count":1,"area":null},{"id":"2407.14043","title":"Kinematics-based 3D Human-Object Interaction Reconstruction from Single View","created":"2024-07-19","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":"2302.06494","title":"Explicit3D: Graph Network with Spatial Inference for Single Image 3D Object Detection","created":"2023-02-13","cited_by_count":0,"area":null},{"id":"2312.00316","title":"Improving Efficiency of DNN-based Relocalization Module for Autonomous Driving with Server-side Computing","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2408.08086","title":"Single-image coherent reconstruction of objects and humans","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2502.18150","title":"Realistic Clothed Human and Object Joint Reconstruction from a Single Image","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2505.04276","title":"HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation","created":"2025-05-07","cited_by_count":0,"area":"diffusion"},{"id":"2508.14358","title":"Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimation","created":"2025-08-20","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}],"next_cursor":null}