{"list":"other","total":94,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1906.12320","title":"PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows","created":"2019-06-28","cited_by_count":488},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2206.04670","title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","created":"2022-06-09","cited_by_count":436},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"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":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2303.06555","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","created":"2023-03-12","cited_by_count":187},{"id":"2007.09545","title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose","created":"2020-07-19","cited_by_count":183},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"2008.04451","title":"Grasping Field: Learning Implicit Representations for Human Grasps","created":"2020-08-10","cited_by_count":179},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2104.03304","title":"Hand-Object Contact Consistency Reasoning for Human Grasps Generation","created":"2021-04-07","cited_by_count":160},{"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":"1904.06830","title":"ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging","created":"2019-04-15","cited_by_count":147},{"id":"2112.11454","title":"GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping","created":"2021-12-21","cited_by_count":144},{"id":"2104.07267","title":"ContactOpt: Optimizing Contact to Improve Grasps","created":"2021-04-15","cited_by_count":139},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138},{"id":"2103.17265","title":"Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors","created":"2021-03-31","cited_by_count":137},{"id":"2210.02697","title":"DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation","created":"2022-10-06","cited_by_count":137},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2012.05522","title":"Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes","created":"2020-12-10","cited_by_count":135},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135},{"id":"1912.02923","title":"Generating 3D People in Scenes without People","created":"2019-12-05","cited_by_count":127},{"id":"2212.07555","title":"IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions","created":"2022-12-14","cited_by_count":124},{"id":"1506.02178","title":"Capturing Hands in Action using Discriminative Salient Points and Physics Simulation","created":"2015-06-06","cited_by_count":115},{"id":"2112.03028","title":"D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions","created":"2021-12-01","cited_by_count":113},{"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":"2209.12354","title":"InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction","created":"2022-09-26","cited_by_count":93},{"id":"2112.10103","title":"SAGA: Stochastic Whole-Body Grasping with Contact","created":"2021-12-19","cited_by_count":91},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83},{"id":"2404.10685","title":"Generating Human Interaction Motions in Scenes with Text Control","created":"2024-04-16","cited_by_count":80},{"id":"2212.10621","title":"Full-Body Articulated Human-Object Interaction","created":"2022-12-20","cited_by_count":78},{"id":"2307.07511","title":"NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis","created":"2023-07-14","cited_by_count":78},{"id":"2104.09194","title":"Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimator","created":"2021-04-19","cited_by_count":71},{"id":"2105.14804","title":"Scene-aware Generative Network for Human Motion Synthesis","created":"2021-05-31","cited_by_count":70},{"id":"2205.07982","title":"TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement","created":"2022-05-16","cited_by_count":70},{"id":"2212.07626","title":"NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions","created":"2022-12-15","cited_by_count":68},{"id":"2403.17827","title":"DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions","created":"2024-03-26","cited_by_count":62},{"id":"2403.12409","title":"ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance","created":"2024-03-19","cited_by_count":59},{"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":"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":"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":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54},{"id":"2404.00299","title":"HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment","created":"2024-03-30","cited_by_count":53},{"id":"2309.07907","title":"Physically Plausible Full-Body Hand-Object Interaction Synthesis","created":"2023-09-14","cited_by_count":52},{"id":"2310.11784","title":"Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts","created":"2023-10-18","cited_by_count":52},{"id":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49},{"id":"2211.11903","title":"FLEX: Full-Body Grasping Without Full-Body Grasps","created":"2022-11-21","cited_by_count":46},{"id":"2202.12825","title":"NeuralHOFusion: Neural Volumetric Rendering under Human-object Interactions","created":"2022-02-25","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":"2306.09337","title":"Generative Proxemics: A Prior for 3D Social Interaction from Images","created":"2023-06-15","cited_by_count":43},{"id":"2310.02242","title":"Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models","created":"2023-10-03","cited_by_count":43},{"id":"2303.13129","title":"Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations","created":"2023-03-23","cited_by_count":42},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41},{"id":"1908.07423","title":"Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control","created":"2019-08-20","cited_by_count":40},{"id":"2304.02061","title":"Generating Continual Human Motion in Diverse 3D Scenes","created":"2023-04-04","cited_by_count":39},{"id":"2312.07063","title":"Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation","created":"2023-12-12","cited_by_count":38},{"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},{"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},{"id":"2209.02485","title":"Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors","created":"2022-09-06","cited_by_count":30},{"id":"2404.04819","title":"Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer","created":"2024-04-07","cited_by_count":29},{"id":"2308.11617","title":"GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistency","created":"2023-08-22","cited_by_count":27},{"id":"2407.12435","title":"F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions","created":"2024-07-17","cited_by_count":24},{"id":"2312.14024","title":"NICP: Neural ICP for 3D Human Registration at Scale","created":"2023-12-21","cited_by_count":21},{"id":"2301.01424","title":"Scene Synthesis from Human Motion","created":"2023-01-04","cited_by_count":20},{"id":"2404.01758","title":"GEARS: Local Geometry-aware Hand-object Interaction Synthesis","created":"2024-04-02","cited_by_count":20},{"id":"2308.12288","title":"CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images","created":"2023-08-23","cited_by_count":19},{"id":"2403.15612","title":"InterFusion: Text-Driven Generation of 3D Human-Object Interaction","created":"2024-03-22","cited_by_count":18},{"id":"2305.14345","title":"NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects","created":"2023-05-23","cited_by_count":17},{"id":"2409.16178","title":"SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image","created":"2024-09-24","cited_by_count":9},{"id":"2405.11481","title":"Physics-aware Hand-object Interaction Denoising","created":"2024-05-19","cited_by_count":8},{"id":"2307.12067","title":"Replay: Multi-modal Multi-view Acted Videos for Casual Holography","created":"2023-07-22","cited_by_count":7},{"id":"2312.10714","title":"Primitive-based 3D Human-Object Interaction Modelling and Programming","created":"2023-12-17","cited_by_count":7},{"id":"2410.17858","title":"Blendify -- Python rendering framework for Blender","created":"2024-10-23","cited_by_count":4}],"next_cursor":null}