{"list":"other","total":81,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"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":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"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":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"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":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218},{"id":"2305.06456","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","created":"2023-05-10","cited_by_count":218},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2009.02119","title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","created":"2020-09-04","cited_by_count":202},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"id":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"id":"2502.01143","title":"ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills","created":"2025-02-03","cited_by_count":130},{"id":"2303.09119","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","created":"2023-03-16","cited_by_count":129},{"id":"2409.14393","title":"MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting","created":"2024-09-22","cited_by_count":116},{"id":"2103.10206","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","created":"2021-03-18","cited_by_count":111},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96},{"id":"2311.17135","title":"TLControl: Trajectory and Language Control for Human Motion Synthesis","created":"2023-11-28","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":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89},{"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":"2211.14304","title":"BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction","created":"2022-11-25","cited_by_count":82},{"id":"2302.03665","title":"HumanMAC: Masked Motion Completion for Human Motion Prediction","created":"2023-02-07","cited_by_count":81},{"id":"1907.04967","title":"Diverse Trajectory Forecasting with Determinantal Point Processes","created":"2019-07-11","cited_by_count":80},{"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":"2203.07706","title":"ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation","created":"2022-03-15","cited_by_count":77},{"id":"2304.02419","title":"TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration","created":"2023-04-05","cited_by_count":76},{"id":"2502.20390","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","created":"2025-02-27","cited_by_count":72},{"id":"2105.14804","title":"Scene-aware Generative Network for Human Motion Synthesis","created":"2021-05-31","cited_by_count":70},{"id":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68},{"id":"2403.13900","title":"CoMo: Controllable Motion Generation through Language Guided Pose Code Editing","created":"2024-03-20","cited_by_count":67},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"1910.11760","title":"Self-supervised Moving Vehicle Tracking with Stereo Sound","created":"2019-10-25","cited_by_count":63},{"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":"2108.08020","title":"Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates","created":"2021-08-18","cited_by_count":58},{"id":"2404.15121","title":"Taming Diffusion Probabilistic Models for Character Control","created":"2024-04-23","cited_by_count":57},{"id":"2306.00416","title":"Interactive Character Control with Auto-Regressive Motion Diffusion Models","created":"2023-06-01","cited_by_count":55},{"id":"2309.11351","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","created":"2023-09-20","cited_by_count":55},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53},{"id":"2503.19901","title":"TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization","created":"2025-03-25","cited_by_count":51},{"id":"2405.07784","title":"Generating Human Motion in 3D Scenes from Text Descriptions","created":"2024-05-13","cited_by_count":49},{"id":"2403.18811","title":"Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment","created":"2024-03-27","cited_by_count":47},{"id":"2405.09814","title":"Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis","created":"2024-05-16","cited_by_count":40},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36},{"id":"2403.13307","title":"LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment","created":"2024-03-20","cited_by_count":33},{"id":"2404.04430","title":"PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos","created":"2024-04-05","cited_by_count":28},{"id":"2312.14828","title":"Plan, Posture and Go: Towards Open-World Text-to-Motion Generation","created":"2023-12-22","cited_by_count":26},{"id":"2407.21136","title":"MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls","created":"2024-07-30","cited_by_count":26},{"id":"2410.10676","title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation","created":"2024-10-14","cited_by_count":25},{"id":"2405.03178","title":"POPDG: Popular 3D Dance Generation with PopDanceSet","created":"2024-05-06","cited_by_count":24},{"id":"2305.12554","title":"CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion","created":"2023-05-21","cited_by_count":21},{"id":"2410.04534","title":"UniMuMo: Unified Text, Music and Motion Generation","created":"2024-10-06","cited_by_count":19},{"id":"2405.13336","title":"SIGGesture: Generalized Co-Speech Gesture Synthesis via Semantic Injection with Large-Scale Pre-Training Diffusion Models","created":"2024-05-22","cited_by_count":18},{"id":"2410.18977","title":"Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing","created":"2024-10-24","cited_by_count":18},{"id":"2310.18986","title":"Controllable Group Choreography using Contrastive Diffusion","created":"2023-10-29","cited_by_count":17},{"id":"2411.06307","title":"Acoustic Volume Rendering for Neural Impulse Response Fields","created":"2024-11-09","cited_by_count":14},{"id":"2402.04356","title":"Bidirectional Autoregressive Diffusion Model for Dance Generation","created":"2024-02-06","cited_by_count":13},{"id":"2407.13083","title":"Modeling and Driving Human Body Soundfields through Acoustic Primitives","created":"2024-07-18","cited_by_count":12},{"id":"2411.19921","title":"SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation","created":"2024-11-29","cited_by_count":12},{"id":"2505.21437","title":"CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects","created":"2025-05-27","cited_by_count":12},{"id":"2506.12199","title":"ViSAGe: Video-to-Spatial Audio Generation","created":"2025-06-13","cited_by_count":11},{"id":"2411.16964","title":"MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning","created":"2024-11-25","cited_by_count":8},{"id":"2405.11690","title":"InterAct: Capture and Modelling of Realistic, Expressive and Interactive Activities between Two Persons in Daily Scenarios","created":"2024-05-19","cited_by_count":7},{"id":"2412.04343","title":"RMD: A Simple Baseline for More General Human Motion Generation via Training-free Retrieval-Augmented Motion Diffuse","created":"2024-12-05","cited_by_count":7},{"id":"2502.14140","title":"ModSkill: Physical Character Skill Modularization","created":"2025-02-19","cited_by_count":7},{"id":"2311.06285","title":"Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio","created":"2023-11-01","cited_by_count":6},{"id":"2412.02419","title":"It Takes Two: Real-time Co-Speech Two-person's Interaction Generation via Reactive Auto-regressive Diffusion Model","created":"2024-12-03","cited_by_count":2}],"next_cursor":null}