{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212},{"id":"2412.03555","title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","created":"2024-12-04","cited_by_count":207},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2306.06362","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","created":"2023-06-10","cited_by_count":167},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145},{"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":"2312.03596","title":"MMM: Generative Masked Motion Model","created":"2023-12-06","cited_by_count":131},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114},{"id":"2312.03913","title":"Controllable Human-Object Interaction Synthesis","created":"2023-12-06","cited_by_count":109},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96},{"id":"2005.05751","title":"Unpaired Motion Style Transfer from Video to Animation","created":"2020-05-12","cited_by_count":94},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"1904.03419","title":"Context-aware Human Motion Prediction","created":"2019-04-06","cited_by_count":84},{"id":"2204.09443","title":"GIMO: Gaze-Informed Human Motion Prediction in Context","created":"2022-04-20","cited_by_count":81},{"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},{"id":"2404.10685","title":"Generating Human Interaction Motions in Scenes with Text Control","created":"2024-04-16","cited_by_count":80},{"id":"2303.17912","title":"CIRCLE: Capture In Rich Contextual Environments","created":"2023-03-31","cited_by_count":79},{"id":"2307.07511","title":"NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis","created":"2023-07-14","cited_by_count":78},{"id":"2201.04439","title":"Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases","created":"2022-01-12","cited_by_count":72},{"id":"2206.03287","title":"NeMF: Neural Motion Fields for Kinematic Animation","created":"2022-06-04","cited_by_count":68},{"id":"2302.05905","title":"Single Motion Diffusion","created":"2023-02-12","cited_by_count":65},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58},{"id":"2410.03187","title":"Autonomous Character-Scene Interaction Synthesis from Text Instruction","created":"2024-10-04","cited_by_count":56},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53},{"id":"2301.02667","title":"Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments","created":"2023-01-09","cited_by_count":51},{"id":"2306.08731","title":"EPIC Fields: Marrying 3D Geometry and Video Understanding","created":"2023-06-14","cited_by_count":49},{"id":"2405.07784","title":"Generating Human Motion in 3D Scenes from Text Descriptions","created":"2024-05-13","cited_by_count":49},{"id":"2403.18118","title":"EgoLifter: Open-world 3D Segmentation for Egocentric Perception","created":"2024-03-26","cited_by_count":47},{"id":"2310.14729","title":"MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion","created":"2023-10-23","cited_by_count":37},{"id":"2112.15012","title":"Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction","created":"2021-12-30","cited_by_count":31},{"id":"2311.16495","title":"Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement","created":"2023-11-28","cited_by_count":31},{"id":"2406.06508","title":"Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer","created":"2024-06-10","cited_by_count":31},{"id":"2103.06498","title":"3D Human Pose, Shape and Texture from Low-Resolution Images and Videos","created":"2021-03-11","cited_by_count":26},{"id":"2509.03883","title":"Human Motion Video Generation: A Survey","created":"2025-09-04","cited_by_count":25},{"id":"2506.18680","title":"DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling","created":"2025-06-23","cited_by_count":21},{"id":"2504.08449","title":"Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input","created":"2025-04-11","cited_by_count":17},{"id":"2508.01126","title":"UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation","created":"2025-08-02","cited_by_count":17},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15},{"id":"2508.13013","title":"EgoTwin: Dreaming Body and View in First Person","created":"2025-08-18","cited_by_count":13},{"id":"2508.14466","title":"LookOut: Real-World Humanoid Egocentric Navigation","created":"2025-08-20","cited_by_count":9},{"id":"2512.22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation","created":"2025-12-28","cited_by_count":7},{"id":"2509.23635","title":"MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing","created":"2025-09-28","cited_by_count":5}],"next_cursor":null}