{"total":44,"rows":[{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485,"area":null},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218,"area":null},{"id":"2108.06720","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","created":"2021-08-15","cited_by_count":109,"area":null},{"id":"2102.06837","title":"Learning Speech-driven 3D Conversational Gestures from Video","created":"2021-02-13","cited_by_count":98,"area":null},{"id":"2108.08020","title":"Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates","created":"2021-08-18","cited_by_count":58,"area":null},{"id":"2111.12159","title":"Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure","created":"2021-11-23","cited_by_count":53,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37,"area":null},{"id":"2310.06238","title":"Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering","created":"2023-10-10","cited_by_count":29,"area":null},{"id":"2205.15608","title":"Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction","created":"2022-05-31","cited_by_count":26,"area":null},{"id":"2212.04638","title":"FLAG3D: A 3D Fitness Activity Dataset with Language Instruction","created":"2022-12-09","cited_by_count":23,"area":null},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22,"area":null},{"id":"2310.06851","title":"BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer","created":"2023-09-07","cited_by_count":21,"area":null},{"id":"2111.06925","title":"Action2video: Generating Videos of Human 3D Actions","created":"2021-11-12","cited_by_count":15,"area":null},{"id":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","cited_by_count":15,"area":null},{"id":"2207.03483","title":"Finding Fallen Objects Via Asynchronous Audio-Visual Integration","created":"2022-07-07","cited_by_count":14,"area":null},{"id":"2405.09266","title":"Dance Any Beat: Blending Beats with Visuals in Dance Video Generation","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2104.01703","title":"FixMyPose: Pose Correctional Captioning and Retrieval","created":"2021-04-04","cited_by_count":12,"area":null},{"id":"2203.02291","title":"Freeform Body Motion Generation from Speech","created":"2022-03-04","cited_by_count":11,"area":null},{"id":"2107.03109","title":"Egocentric Videoconferencing","created":"2021-07-07","cited_by_count":10,"area":null},{"id":"2301.06690","title":"Audio2Gestures: Generating Diverse Gestures from Audio","created":"2023-01-17","cited_by_count":10,"area":null},{"id":"2410.05791","title":"F\\\"urElise: Capturing and Physically Synthesizing Hand Motions of Piano Performance","created":"2024-10-08","cited_by_count":10,"area":null},{"id":"2211.16210","title":"PaCMO: Partner Dependent Human Motion Generation in Dyadic Human Activity using Neural Operators","created":"2022-11-25","cited_by_count":8,"area":null},{"id":"2208.01917","title":"Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding","created":"2022-08-03","cited_by_count":7,"area":null},{"id":"2110.13412","title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","created":"2021-10-26","cited_by_count":6,"area":null},{"id":"2206.13502","title":"Programmatic Concept Learning for Human Motion Description and Synthesis","created":"2022-06-27","cited_by_count":5,"area":null},{"id":"2507.19836","title":"ChoreoMuse: Robust Music-to-Dance Video Generation with Style Transfer and Beat-Adherent Motion","created":"2025-07-26","cited_by_count":4,"area":null},{"id":"2203.12829","title":"AIMusicGuru: Music Assisted Human Pose Correction","created":"2022-03-24","cited_by_count":3,"area":null},{"id":"2406.06375","title":"MOSA: Music Motion with Semantic Annotation Dataset for Cross-Modal Music Processing","created":"2024-06-10","cited_by_count":3,"area":null},{"id":"2411.07165","title":"Acoustic-based 3D Human Pose Estimation Robust to Human Position","created":"2024-11-08","cited_by_count":2,"area":null},{"id":"2603.10446","title":"SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.11042","title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2311.07630","title":"Cross-modal Generative Model for Visual-Guided Binaural Stereo Generation","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2407.01244","title":"CLHOP: Combined Audio-Video Learning for Horse 3D Pose and Shape Estimation","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2410.05964","title":"STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2503.00389","title":"BGM2Pose: Active 3D Human Pose Estimation with Non-Stationary Sounds","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2604.23886","title":"MUSIC: Learning Muscle-Driven Dexterous Hand Control","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2108.11773","title":"Multi-Modulation Network for Audio-Visual Event Localization","created":"2021-08-26","cited_by_count":0,"area":null},{"id":"2305.12887","title":"ZS-MSTM: Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2411.13607","title":"VioPose: Violin Performance 4D Pose Estimation by Hierarchical Audiovisual Inference","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2507.00669","title":"Audio-3DVG: Unified Audio -- Point Cloud Fusion for 3D Visual Grounding","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2507.04062","title":"Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic","created":"2025-07-05","cited_by_count":0,"area":null},{"id":"2604.09692","title":"Tipiano: Cascaded Piano Hand Motion Synthesis via Fingertip Priors","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2608.24909","title":"Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans","created":"2026-07-22","cited_by_count":0,"area":null}],"next_cursor":null}