{"list":"other","total":64,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1711.07566","title":"Neural 3D Mesh Renderer","created":"2017-11-20","cited_by_count":437},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238},{"id":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169},{"id":"2104.03304","title":"Hand-Object Contact Consistency Reasoning for Human Grasps Generation","created":"2021-04-07","cited_by_count":160},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2007.15649","title":"Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild","created":"2020-07-30","cited_by_count":152},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"1907.11346","title":"Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image","created":"2019-07-26","cited_by_count":132},{"id":"1912.02923","title":"Generating 3D People in Scenes without People","created":"2019-12-05","cited_by_count":127},{"id":"1506.02178","title":"Capturing Hands in Action using Discriminative Salient Points and Physics Simulation","created":"2015-06-06","cited_by_count":115},{"id":"2012.00619","title":"We are More than Our Joints: Predicting how 3D Bodies Move","created":"2020-12-01","cited_by_count":115},{"id":"2312.03913","title":"Controllable Human-Object Interaction Synthesis","created":"2023-12-06","cited_by_count":109},{"id":"2204.02445","title":"CHORE: Contact, Human and Object REconstruction from a single RGB image","created":"2022-04-05","cited_by_count":95},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"2209.12354","title":"InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction","created":"2022-09-26","cited_by_count":93},{"id":"2312.06553","title":"HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models","created":"2023-12-11","cited_by_count":93},{"id":"2203.16427","title":"Balanced MSE for Imbalanced Visual Regression","created":"2022-03-30","cited_by_count":89},{"id":"2303.17912","title":"CIRCLE: Capture In Rich Contextual Environments","created":"2023-03-31","cited_by_count":79},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76},{"id":"2212.07626","title":"NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions","created":"2022-12-15","cited_by_count":68},{"id":"2303.16479","title":"Visibility Aware Human-Object Interaction Tracking from Single RGB Camera","created":"2023-03-29","cited_by_count":58},{"id":"2212.04360","title":"MIME: Human-Aware 3D Scene Generation","created":"2022-12-08","cited_by_count":57},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56},{"id":"2012.01591","title":"Holistic 3D Human and Scene Mesh Estimation from Single View Images","created":"2020-12-02","cited_by_count":54},{"id":"2008.11469","title":"SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation","created":"2020-08-26","cited_by_count":52},{"id":"2002.12625","title":"4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras","created":"2020-02-28","cited_by_count":49},{"id":"2105.02467","title":"Body Meshes as Points","created":"2021-05-06","cited_by_count":45},{"id":"2205.15410","title":"LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors","created":"2022-05-30","cited_by_count":44},{"id":"2312.08869","title":"I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions","created":"2023-12-10","cited_by_count":44},{"id":"2310.02242","title":"Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models","created":"2023-10-03","cited_by_count":43},{"id":"2108.08420","title":"D3D-HOI: Dynamic 3D Human-Object Interactions from Videos","created":"2021-08-19","cited_by_count":39},{"id":"2108.00362","title":"Neural Free-Viewpoint Performance Rendering under Complex Human-object Interactions","created":"2021-08-01","cited_by_count":37},{"id":"2403.12835","title":"AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents","created":"2024-03-19","cited_by_count":32},{"id":"2108.08844","title":"Gravity-Aware Monocular 3D Human-Object Reconstruction","created":"2021-08-19","cited_by_count":30},{"id":"2403.15612","title":"InterFusion: Text-Driven Generation of 3D Human-Object Interaction","created":"2024-03-22","cited_by_count":18},{"id":"2302.01058","title":"IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation","created":"2023-02-02","cited_by_count":9},{"id":"2403.11237","title":"FORCE: Physics-aware Human-object Interaction","created":"2024-03-17","cited_by_count":7},{"id":"2202.04533","title":"NIMBLE: A Non-rigid Hand Model with Bones and Muscles","created":"2022-02-09","cited_by_count":6}],"next_cursor":null}