{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"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":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2305.06456","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","created":"2023-05-10","cited_by_count":218},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","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":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"2311.17135","title":"TLControl: Trajectory and Language Control for Human Motion Synthesis","created":"2023-11-28","cited_by_count":94},{"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":"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":"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":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68},{"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":"2309.11351","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","created":"2023-09-20","cited_by_count":55},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","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":"2503.19901","title":"TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization","created":"2025-03-25","cited_by_count":51},{"id":"2410.10010","title":"InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling","created":"2024-10-13","cited_by_count":47},{"id":"2207.01685","title":"Interaction Transformer for Human Reaction Generation","created":"2022-07-04","cited_by_count":42},{"id":"2403.13307","title":"LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment","created":"2024-03-20","cited_by_count":33},{"id":"2506.05554","title":"EX-4D: EXtreme Viewpoint 4D Video Synthesis via Depth Watertight Mesh","created":"2025-06-05","cited_by_count":32},{"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":"2210.05976","title":"Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction","created":"2022-10-12","cited_by_count":28},{"id":"2305.12554","title":"CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion","created":"2023-05-21","cited_by_count":21},{"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":"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":"2503.01291","title":"SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance","created":"2025-03-03","cited_by_count":16},{"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":"2507.11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio","created":"2025-07-16","cited_by_count":12},{"id":"2510.06504","title":"Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation","created":"2025-10-07","cited_by_count":11},{"id":"2508.14466","title":"LookOut: Real-World Humanoid Egocentric Navigation","created":"2025-08-20","cited_by_count":9},{"id":"2411.16964","title":"MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning","created":"2024-11-25","cited_by_count":8},{"id":"2502.14140","title":"ModSkill: Physical Character Skill Modularization","created":"2025-02-19","cited_by_count":7},{"id":"2503.16451","title":"Think-Then-React: Towards Unconstrained Human Action-to-Reaction Generation","created":"2025-02-19","cited_by_count":7},{"id":"2509.24099","title":"Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flow","created":"2025-09-28","cited_by_count":6},{"id":"2506.01579","title":"HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception","created":"2025-06-02","cited_by_count":5},{"id":"2509.19259","title":"Moving by Looking: Towards Vision-Driven Avatar Motion Generation","created":"2025-09-23","cited_by_count":4},{"id":"2409.11602","title":"React to This! How Humans Challenge Interactive Agents using Nonverbal Behaviors","created":"2024-09-17","cited_by_count":3}],"next_cursor":null}