{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"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":"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":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"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":"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":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"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":"1902.03451","title":"3D Hand Shape and Pose from Images in the Wild","created":"2019-02-09","cited_by_count":190},{"id":"1911.01255","title":"pyannote.audio: neural building blocks for speaker diarization","created":"2019-11-04","cited_by_count":181},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180},{"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":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153},{"id":"2303.09119","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","created":"2023-03-16","cited_by_count":129},{"id":"2108.06720","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","created":"2021-08-15","cited_by_count":109},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107},{"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":"2102.06837","title":"Learning Speech-driven 3D Conversational Gestures from Video","created":"2021-02-13","cited_by_count":98},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98},{"id":"2311.17590","title":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","created":"2023-11-29","cited_by_count":86},{"id":"2008.08171","title":"Learning to Generate Diverse Dance Motions with Transformer","created":"2020-08-18","cited_by_count":85},{"id":"2305.04919","title":"DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models","created":"2023-05-08","cited_by_count":85},{"id":"2209.07556","title":"ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech","created":"2022-09-15","cited_by_count":84},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82},{"id":"2007.12553","title":"Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach","created":"2020-07-24","cited_by_count":65},{"id":"2112.13715","title":"SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos","created":"2021-12-27","cited_by_count":64},{"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":"2312.08985","title":"OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers","created":"2023-12-14","cited_by_count":47},{"id":"2403.17936","title":"ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis","created":"2024-03-26","cited_by_count":41},{"id":"2305.18891","title":"EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation","created":"2023-05-30","cited_by_count":40},{"id":"2309.09294","title":"LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation","created":"2023-09-17","cited_by_count":40},{"id":"2405.09814","title":"Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis","created":"2024-05-16","cited_by_count":40},{"id":"2307.16620","title":"Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics","created":"2023-07-31","cited_by_count":32},{"id":"2404.00368","title":"Towards Variable and Coordinated Holistic Co-Speech Motion Generation","created":"2024-03-30","cited_by_count":29},{"id":"2308.12646","title":"The GENEA Challenge 2023: A large scale evaluation of gesture generation models in monadic and dyadic settings","created":"2023-08-24","cited_by_count":28},{"id":"2303.01765","title":"Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand Disentanglement","created":"2023-03-03","cited_by_count":18},{"id":"2310.18986","title":"Controllable Group Choreography using Contrastive Diffusion","created":"2023-10-29","cited_by_count":17},{"id":"2311.17532","title":"Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation","created":"2023-11-29","cited_by_count":17},{"id":"2210.05668","title":"Understanding Embodied Reference with Touch-Line Transformer","created":"2022-10-11","cited_by_count":16}],"next_cursor":null}