{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"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":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2303.00747","title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio","created":"2023-03-01","cited_by_count":326},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"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":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178},{"id":"2306.11290","title":"Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation","created":"2023-06-20","cited_by_count":167},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"id":"2012.05522","title":"Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes","created":"2020-12-10","cited_by_count":135},{"id":"2303.09119","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","created":"2023-03-16","cited_by_count":129},{"id":"2305.12411","title":"Synthesizing Diverse Human Motions in 3D Indoor Scenes","created":"2023-05-21","cited_by_count":109},{"id":"2401.00374","title":"EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling","created":"2023-12-31","cited_by_count":105},{"id":"1908.09186","title":"Efficient Learning on Point Clouds with Basis Point Sets","created":"2019-08-24","cited_by_count":103},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86},{"id":"2305.04919","title":"DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models","created":"2023-05-08","cited_by_count":85},{"id":"2001.09326","title":"Gesticulator: A framework for semantically-aware speech-driven gesture generation","created":"2020-01-25","cited_by_count":84},{"id":"2404.10685","title":"Generating Human Interaction Motions in Scenes with Text Control","created":"2024-04-16","cited_by_count":80},{"id":"1903.05690","title":"Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments","created":"2019-03-13","cited_by_count":72},{"id":"2602.15989","title":"SAM 3D Body: Robust Full-Body Human Mesh Recovery","created":"2026-02-17","cited_by_count":69},{"id":"2301.05339","title":"A Comprehensive Review of Data-Driven Co-Speech Gesture Generation","created":"2023-01-13","cited_by_count":66},{"id":"2401.04747","title":"DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation","created":"2024-01-09","cited_by_count":62},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56},{"id":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55},{"id":"2304.05690","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","created":"2023-04-12","cited_by_count":49},{"id":"2412.10523","title":"The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion","created":"2024-12-13","cited_by_count":46},{"id":"2501.18898","title":"GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling","created":"2025-01-31","cited_by_count":44},{"id":"2403.17936","title":"ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis","created":"2024-03-26","cited_by_count":41},{"id":"2305.11094","title":"QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation","created":"2023-05-18","cited_by_count":40},{"id":"2410.00464","title":"Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation","created":"2024-10-01","cited_by_count":35},{"id":"2510.16258","title":"Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset","created":"2025-10-17","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":"2507.19359","title":"SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning","created":"2025-07-25","cited_by_count":17},{"id":"2603.03282","title":"MIBURI: Towards Expressive Interactive Gesture Synthesis","created":"2026-03-03","cited_by_count":9},{"id":"2507.22731","title":"GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded-Synchronized Retrieval-Augmented Generation","created":"2025-07-30","cited_by_count":7},{"id":"2512.14234","title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","created":"2025-12-16","cited_by_count":6},{"id":"2509.23612","title":"InteractMove: Text-Controlled Human-Object Interaction Generation in 3D Scenes with Movable Objects","created":"2025-09-28","cited_by_count":3},{"id":"2512.12664","title":"InteracTalker: Prompt-Based Human-Object Interaction with Co-Speech Gesture Generation","created":"2025-12-14","cited_by_count":3},{"id":"2601.20835","title":"Open-Vocabulary Functional 3D Human-Scene Interaction Generation","created":"2026-01-28","cited_by_count":3},{"id":"2602.20476","title":"SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens","created":"2026-02-24","cited_by_count":3},{"id":"2605.28272","title":"EchoAvatar: Real-time Generative Avatar Animation from Audio Streams","created":"2026-05-27","cited_by_count":2},{"id":"2605.01036","title":"InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene","created":"2026-05-01","cited_by_count":1}],"next_cursor":null}