{"list":"other","total":63,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"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":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"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":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"id":"2108.06720","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","created":"2021-08-15","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":"2102.06837","title":"Learning Speech-driven 3D Conversational Gestures from Video","created":"2021-02-13","cited_by_count":98},{"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":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82},{"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":"2403.10518","title":"Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives","created":"2024-03-15","cited_by_count":61},{"id":"2403.09471","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","created":"2024-03-14","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":"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":"2303.08658","title":"Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry","created":"2023-03-15","cited_by_count":35},{"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":"2412.16563","title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","created":"2024-12-21","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":"2412.06786","title":"Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis","created":"2024-12-09","cited_by_count":26},{"id":"2407.10061","title":"InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation","created":"2024-07-14","cited_by_count":23},{"id":"2308.01850","title":"Synthesizing Long-Term Human Motions with Diffusion Models via Coherent Sampling","created":"2023-08-03","cited_by_count":19},{"id":"2505.17543","title":"MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation","created":"2025-05-23","cited_by_count":18},{"id":"2504.09209","title":"EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation","created":"2025-04-12","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":"2310.12678","title":"TapMo: Shape-aware Motion Generation of Skeleton-free Characters","created":"2023-10-19","cited_by_count":16},{"id":"2404.11375","title":"Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion","created":"2024-04-17","cited_by_count":16},{"id":"2310.10300","title":"BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval","created":"2023-10-16","cited_by_count":12},{"id":"2411.18303","title":"InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillation","created":"2024-11-27","cited_by_count":12},{"id":"2511.10076","title":"Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints","created":"2025-11-13","cited_by_count":12},{"id":"2511.21029","title":"FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation","created":"2025-11-26","cited_by_count":11},{"id":"2512.18181","title":"MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation","created":"2025-12-20","cited_by_count":9},{"id":"2412.19123","title":"CoheDancers: Enhancing Interactive Group Dance Generation through Music-Driven Coherence Decomposition","created":"2024-12-26","cited_by_count":8},{"id":"2605.06064","title":"PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers","created":"2026-05-07","cited_by_count":7},{"id":"2403.10805","title":"Speech-driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference","created":"2024-03-16","cited_by_count":6},{"id":"2505.11013","title":"Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion","created":"2025-05-16","cited_by_count":6},{"id":"2604.08896","title":"GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing","created":"2026-04-10","cited_by_count":6},{"id":"2605.08729","title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","created":"2026-05-09","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":"2606.22905","title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","created":"2026-06-22","cited_by_count":5},{"id":"2601.21904","title":"Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning","created":"2026-01-29","cited_by_count":4},{"id":"2209.13204","title":"NEURAL MARIONETTE: A Transformer-based Multi-action Human Motion Synthesis System","created":"2022-09-27","cited_by_count":3},{"id":"2504.11749","title":"SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation","created":"2025-04-16","cited_by_count":3},{"id":"2506.21912","title":"Generating Attribute-Aware Human Motions from Textual Prompt","created":"2025-06-27","cited_by_count":3},{"id":"2511.04192","title":"AStF: Motion Style Transfer via Adaptive Statistics Fusor","created":"2025-11-06","cited_by_count":3},{"id":"2606.30019","title":"OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data","created":"2026-06-29","cited_by_count":3},{"id":"2503.23266","title":"OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition","created":"2025-03-30","cited_by_count":2},{"id":"2602.18432","title":"SARAH: Spatially Aware Real-time Agentic Humans","created":"2026-02-20","cited_by_count":2},{"id":"2605.27055","title":"Semantic-Aware Motion Encoding for Topology-Agnostic Character Animation","created":"2026-05-26","cited_by_count":2}],"next_cursor":null}