{"list":"other","total":84,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"1908.04616","title":"Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data","created":"2019-08-13","cited_by_count":532},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"2003.08386","title":"DLow: Diversifying Latent Flows for Diverse Human Motion Prediction","created":"2020-03-18","cited_by_count":185},{"id":"2103.14274","title":"Character Controllers Using Motion VAEs","created":"2021-03-26","cited_by_count":184},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"id":"1711.09561","title":"HP-GAN: Probabilistic 3D human motion prediction via GAN","created":"2017-11-27","cited_by_count":176},{"id":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"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":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146},{"id":"2112.11454","title":"GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping","created":"2021-12-21","cited_by_count":144},{"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":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"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":"1805.00655","title":"Convolutional Sequence to Sequence Model for Human Dynamics","created":"2018-05-02","cited_by_count":115},{"id":"2108.06720","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","created":"2021-08-15","cited_by_count":109},{"id":"2305.12411","title":"Synthesizing Diverse Human Motions in 3D Indoor Scenes","created":"2023-05-21","cited_by_count":109},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"2103.16397","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","created":"2021-03-30","cited_by_count":100},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96},{"id":"2309.07918","title":"Unified Human-Scene Interaction via Prompted Chain-of-Contacts","created":"2023-09-14","cited_by_count":94},{"id":"2205.13001","title":"Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis","created":"2022-05-25","cited_by_count":91},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83},{"id":"2303.17912","title":"CIRCLE: Capture In Rich Contextual Environments","created":"2023-03-31","cited_by_count":79},{"id":"2212.10621","title":"Full-Body Articulated Human-Object Interaction","created":"2022-12-20","cited_by_count":78},{"id":"2301.02508","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","created":"2023-01-06","cited_by_count":78},{"id":"1903.05690","title":"Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments","created":"2019-03-13","cited_by_count":72},{"id":"1909.01507","title":"Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense","created":"2019-09-04","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":"2203.00843","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","created":"2022-03-02","cited_by_count":70},{"id":"2109.09913","title":"Physics-based Human Motion Estimation and Synthesis from Videos","created":"2021-09-21","cited_by_count":66},{"id":"2008.09241","title":"Learning Affordance Landscapes for Interaction Exploration in 3D Environments","created":"2020-08-21","cited_by_count":65},{"id":"2304.10417","title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation","created":"2023-04-20","cited_by_count":64},{"id":"2112.09251","title":"The Wanderings of Odysseus in 3D Scenes","created":"2021-12-16","cited_by_count":59},{"id":"2304.14406","title":"Putting People in Their Place: Affordance-Aware Human Insertion into Scenes","created":"2023-04-27","cited_by_count":53},{"id":"2204.02320","title":"Learning Generalizable Dexterous Manipulation from Human Grasp Affordance","created":"2022-04-05","cited_by_count":51},{"id":"2107.12514","title":"Language Grounding with 3D Objects","created":"2021-07-26","cited_by_count":43},{"id":"1804.03080","title":"Binge Watching: Scaling Affordance Learning from Sitcoms","created":"2018-04-09","cited_by_count":41},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41},{"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":"2109.03413","title":"YouRefIt: Embodied Reference Understanding with Language and Gesture","created":"2021-09-08","cited_by_count":33},{"id":"1910.11669","title":"Learning Task-Oriented Grasping from Human Activity Datasets","created":"2019-10-25","cited_by_count":32},{"id":"2403.12835","title":"AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents","created":"2024-03-19","cited_by_count":32},{"id":"2210.03954","title":"Contact-aware Human Motion Forecasting","created":"2022-10-08","cited_by_count":27},{"id":"2310.15599","title":"Grasp Multiple Objects with One Hand","created":"2023-10-24","cited_by_count":18}],"next_cursor":null}