{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2302.04867","title":"UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models","created":"2023-02-09","cited_by_count":450},{"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":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","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":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"id":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168},{"id":"2409.06662","title":"World-Grounded Human Motion Recovery via Gravity-View Coordinates","created":"2024-09-10","cited_by_count":137},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134},{"id":"2312.03596","title":"MMM: Generative Masked Motion Model","created":"2023-12-06","cited_by_count":131},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106},{"id":"2308.16894","title":"EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild","created":"2023-08-31","cited_by_count":97},{"id":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91},{"id":"2401.08559","title":"Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation","created":"2024-01-16","cited_by_count":91},{"id":"2212.03741","title":"FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation","created":"2022-12-07","cited_by_count":88},{"id":"2411.16575","title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","created":"2024-11-25","cited_by_count":85},{"id":"2304.02419","title":"TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration","created":"2023-04-05","cited_by_count":76},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"2403.10518","title":"Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives","created":"2024-03-15","cited_by_count":61},{"id":"2206.07036","title":"Accurate 3D Body Shape Regression using Metric and Semantic Attributes","created":"2022-06-14","cited_by_count":50},{"id":"2505.01425","title":"GENMO: A GENeralist Model for Human MOtion","created":"2025-05-02","cited_by_count":49},{"id":"2405.16273","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","created":"2024-05-25","cited_by_count":38},{"id":"2502.02358","title":"MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm","created":"2025-02-04","cited_by_count":30},{"id":"2407.21136","title":"MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls","created":"2024-07-30","cited_by_count":26},{"id":"2410.20389","title":"Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns","created":"2024-10-27","cited_by_count":21},{"id":"2409.03944","title":"HUMOS: Human Motion Model Conditioned on Body Shape","created":"2024-09-05","cited_by_count":20},{"id":"2312.10993","title":"Realistic Human Motion Generation with Cross-Diffusion Models","created":"2023-12-18","cited_by_count":17},{"id":"2504.03639","title":"Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions","created":"2025-04-04","cited_by_count":11},{"id":"2406.01867","title":"MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training","created":"2024-06-04","cited_by_count":9},{"id":"2411.17335","title":"VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension","created":"2024-11-26","cited_by_count":9},{"id":"2308.07415","title":"Semantify: Simplifying the Control of 3D Morphable Models using CLIP","created":"2023-08-14","cited_by_count":8},{"id":"2410.03556","title":"BodyShapeGPT: SMPL Body Shape Manipulation with LLMs","created":"2024-09-18","cited_by_count":6},{"id":"2503.04257","title":"How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects","created":"2025-03-06","cited_by_count":5},{"id":"2506.21912","title":"Generating Attribute-Aware Human Motions from Textual Prompt","created":"2025-06-27","cited_by_count":3},{"id":"2404.12886","title":"MCM: Multi-condition Motion Synthesis Framework","created":"2024-04-19","cited_by_count":2},{"id":"2502.02063","title":"CASIM: Composite Aware Semantic Injection for Text to Motion Generation","created":"2025-02-04","cited_by_count":2},{"id":"2505.10810","title":"MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human Motion Generation","created":"2025-05-16","cited_by_count":2}],"next_cursor":null}