{"list":"other","total":82,"rows":[{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2007.09545","title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose","created":"2020-07-19","cited_by_count":183},{"id":"2202.08227","title":"Ditto: Building Digital Twins of Articulated Objects from Interaction","created":"2022-02-16","cited_by_count":156},{"id":"2211.05272","title":"GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts","created":"2022-11-10","cited_by_count":139},{"id":"2507.12440","title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","created":"2025-07-16","cited_by_count":128},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124},{"id":"2205.02836","title":"Neural 3D Scene Reconstruction with the Manhattan-world Assumption","created":"2022-05-05","cited_by_count":123},{"id":"1903.03911","title":"Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes","created":"2019-03-10","cited_by_count":119},{"id":"2308.07391","title":"PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects","created":"2023-08-14","cited_by_count":118},{"id":"2405.11656","title":"URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images","created":"2024-05-19","cited_by_count":111},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104},{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102},{"id":"2410.13882","title":"Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model","created":"2024-10-03","cited_by_count":96},{"id":"2401.11439","title":"General Flow as Foundation Affordance for Scalable Robot Learning","created":"2024-01-21","cited_by_count":85},{"id":"2202.08432","title":"AKB-48: A Real-World Articulated Object Knowledge Base","created":"2022-02-17","cited_by_count":82},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2008.10518","title":"ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory","created":"2020-08-24","cited_by_count":70},{"id":"2404.01440","title":"Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects","created":"2024-04-01","cited_by_count":69},{"id":"2410.16499","title":"SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects","created":"2024-10-21","cited_by_count":69},{"id":"2502.19459","title":"ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting","created":"2025-02-26","cited_by_count":67},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66},{"id":"2212.07766","title":"DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients","created":"2022-12-15","cited_by_count":60},{"id":"2407.04689","title":"RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation","created":"2024-07-05","cited_by_count":58},{"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},{"id":"2309.03891","title":"ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation","created":"2023-09-07","cited_by_count":55},{"id":"2203.16421","title":"OPD: Single-view 3D Openable Part Detection","created":"2022-03-30","cited_by_count":54},{"id":"2409.18121","title":"Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction","created":"2024-09-26","cited_by_count":54},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","cited_by_count":54},{"id":"2306.08731","title":"EPIC Fields: Marrying 3D Geometry and Video Understanding","created":"2023-06-14","cited_by_count":49},{"id":"2503.07135","title":"VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation","created":"2025-03-10","cited_by_count":46},{"id":"1712.02310","title":"From Lifestyle Vlogs to Everyday Interactions","created":"2017-12-06","cited_by_count":42},{"id":"2507.12465","title":"PhysX-3D: Physical-Grounded 3D Asset Generation","created":"2025-07-16","cited_by_count":42},{"id":"2108.08420","title":"D3D-HOI: Dynamic 3D Human-Object Interactions from Videos","created":"2021-08-19","cited_by_count":39},{"id":"2303.14087","title":"OPDMulti: Openable Part Detection for Multiple Objects","created":"2023-03-24","cited_by_count":39},{"id":"2303.17504","title":"3D Line Mapping Revisited","created":"2023-03-30","cited_by_count":39},{"id":"2203.16531","title":"Understanding 3D Object Articulation in Internet Videos","created":"2022-03-30","cited_by_count":36},{"id":"2302.14268","title":"Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance","created":"2023-02-28","cited_by_count":26},{"id":"2507.05763","title":"DreamArt: Generating Interactable Articulated Objects from a Single Image","created":"2025-07-08","cited_by_count":25},{"id":"2512.24766","title":"Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow","created":"2025-12-31","cited_by_count":25},{"id":"2205.03721","title":"Category-Independent Articulated Object Tracking with Factor Graphs","created":"2022-05-07","cited_by_count":24},{"id":"2305.16314","title":"Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance","created":"2023-05-25","cited_by_count":19},{"id":"2506.08334","title":"iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos","created":"2025-06-10","cited_by_count":19},{"id":"2509.01708","title":"Articulated Object Estimation in the Wild","created":"2025-09-01","cited_by_count":19},{"id":"2108.05875","title":"Distributional Depth-Based Estimation of Object Articulation Models","created":"2021-08-12","cited_by_count":18},{"id":"2411.16310","title":"Functionality understanding and segmentation in 3D scenes","created":"2024-11-25","cited_by_count":17},{"id":"2508.14891","title":"GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objects","created":"2025-08-20","cited_by_count":17},{"id":"1904.04882","title":"Contextual Attention for Hand Detection in the Wild","created":"2019-04-09","cited_by_count":16},{"id":"2409.06703","title":"LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation","created":"2024-09-10","cited_by_count":16},{"id":"2509.17647","title":"VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video","created":"2025-09-22","cited_by_count":15},{"id":"2303.17774","title":"Semi-Weakly Supervised Object Kinematic Motion Prediction","created":"2023-03-31","cited_by_count":14},{"id":"2403.14937","title":"Survey on Modeling of Human-made Articulated Objects","created":"2024-03-22","cited_by_count":14},{"id":"2503.21313","title":"HORT: Monocular Hand-held Objects Reconstruction with Transformers","created":"2025-03-27","cited_by_count":11},{"id":"2507.02600","title":"ArtGS:3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects","created":"2025-07-03","cited_by_count":11},{"id":"2309.16343","title":"Online Estimation of Articulated Objects with Factor Graphs using Vision and Proprioceptive Sensing","created":"2023-09-28","cited_by_count":10},{"id":"2508.02146","title":"ScrewSplat: An End-to-End Method for Articulated Object Recognition","created":"2025-08-04","cited_by_count":9},{"id":"2512.14671","title":"ART: Articulated Reconstruction Transformer","created":"2025-12-16","cited_by_count":9},{"id":"1412.0630","title":"Batch Nonlinear Continuous-Time Trajectory Estimation as Exactly Sparse Gaussian Process Regression","created":"2014-12-01","cited_by_count":8},{"id":"2108.02708","title":"Object Wake-up: 3D Object Rigging from a Single Image","created":"2021-08-05","cited_by_count":8},{"id":"2209.05612","title":"Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and Challenges","created":"2022-09-12","cited_by_count":8},{"id":"2602.22209","title":"WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videos","created":"2026-02-25","cited_by_count":8},{"id":"2510.11340","title":"REACT3D: Recovering Articulations for Interactive Physical 3D Scenes","created":"2025-10-13","cited_by_count":7},{"id":"2512.24845","title":"ArtiSG: Functional 3D Scene Graph Construction via Human-demonstrated Articulated Objects Manipulation","created":"2025-12-31","cited_by_count":5},{"id":"2508.16465","title":"HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images","created":"2025-08-22","cited_by_count":3},{"id":"2212.01331","title":"Surface Normal Clustering for Implicit Representation of Manhattan Scenes","created":"2022-12-02","cited_by_count":2}],"next_cursor":null}