{"list":"other","total":62,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218},{"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":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"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":"1911.07023","title":"Effectively Unbiased FID and Inception Score and where to find them","created":"2019-11-16","cited_by_count":165},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"id":"2303.09119","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","created":"2023-03-16","cited_by_count":129},{"id":"1810.12541","title":"Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robots","created":"2018-10-30","cited_by_count":110},{"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":"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":"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":"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":"1903.03369","title":"Analyzing Input and Output Representations for Speech-Driven Gesture Generation","created":"2019-03-08","cited_by_count":52},{"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":"2208.10441","title":"The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation","created":"2022-08-22","cited_by_count":40},{"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":"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":"2312.04466","title":"Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion","created":"2023-12-07","cited_by_count":39},{"id":"2102.11617","title":"A large, crowdsourced evaluation of gesture generation systems on common data: The GENEA Challenge 2020","created":"2021-02-23","cited_by_count":38},{"id":"2006.09888","title":"Let's Face It: Probabilistic Multi-modal Interlocutor-aware Generation of Facial Gestures in Dyadic Settings","created":"2020-06-11","cited_by_count":36},{"id":"2412.16563","title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","created":"2024-12-21","cited_by_count":32},{"id":"2303.08737","title":"Evaluating gesture generation in a large-scale open challenge: The GENEA Challenge 2022","created":"2023-03-15","cited_by_count":29},{"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":"2309.05455","title":"Diffusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation","created":"2023-09-11","cited_by_count":28},{"id":"2412.06786","title":"Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis","created":"2024-12-09","cited_by_count":26},{"id":"2101.03769","title":"A Review of Evaluation Practices of Gesture Generation in Embodied Conversational Agents","created":"2021-01-11","cited_by_count":24},{"id":"2310.06851","title":"BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer","created":"2023-09-07","cited_by_count":21},{"id":"2007.09170","title":"Moving fast and slow: Analysis of representations and post-processing in speech-driven automatic gesture generation","created":"2020-07-16","cited_by_count":20},{"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":"2311.17532","title":"Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation","created":"2023-11-29","cited_by_count":17},{"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":"2311.18168","title":"Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications","created":"2023-11-30","cited_by_count":15},{"id":"2308.13879","title":"The DiffuseStyleGesture+ entry to the GENEA Challenge 2023","created":"2023-08-26","cited_by_count":14},{"id":"2305.10608","title":"Investigating Range-Equalizing Bias in Mean Opinion Score Ratings of Synthesized Speech","created":"2023-05-17","cited_by_count":13},{"id":"2108.05709","title":"To Rate or Not To Rate: Investigating Evaluation Methods for Generated Co-Speech Gestures","created":"2021-08-12","cited_by_count":12},{"id":"2107.00712","title":"Passing a Non-verbal Turing Test: Evaluating Gesture Animations Generated from Speech","created":"2021-07-01","cited_by_count":11},{"id":"2206.11461","title":"Towards Better User Studies in Computer Graphics and Vision","created":"2022-06-23","cited_by_count":11},{"id":"2507.20220","title":"Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models","created":"2025-07-27","cited_by_count":11},{"id":"2502.13133","title":"AV-Flow: Transforming Text to Audio-Visual Human-like Interactions","created":"2025-02-18","cited_by_count":9},{"id":"2305.01241","title":"AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis","created":"2023-05-02","cited_by_count":8},{"id":"2503.01175","title":"HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation","created":"2025-03-03","cited_by_count":6},{"id":"2503.13229","title":"HoloGest: Decoupled Diffusion and Motion Priors for Generating Holisticly Expressive Co-speech Gestures","created":"2025-03-17","cited_by_count":5},{"id":"2504.19056","title":"Generative AI for Character Animation: A Comprehensive Survey of Techniques, Applications, and Future Directions","created":"2025-04-27","cited_by_count":3},{"id":"2506.23777","title":"Synthetically Expressive: Evaluating gesture and voice for emotion and empathy in VR and 2D scenarios","created":"2025-06-30","cited_by_count":1}],"next_cursor":null}