{"total":583,"rows":[{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311,"area":null},{"id":"2410.06158","title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","created":"2024-10-08","cited_by_count":296,"area":null},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236,"area":null},{"id":"2402.17485","title":"EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","created":"2024-02-27","cited_by_count":235,"area":"diffusion"},{"id":"2112.01554","title":"Neural Head Avatars from Monocular RGB Videos","created":"2021-12-02","cited_by_count":213,"area":null},{"id":"2212.07422","title":"ECON: Explicit Clothed humans Optimized via Normal integration","created":"2022-12-14","cited_by_count":199,"area":null},{"id":"2407.08136","title":"EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions","created":"2024-07-11","cited_by_count":196,"area":null},{"id":"2403.17694","title":"AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation","created":"2024-03-26","cited_by_count":194,"area":null},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174,"area":null},{"id":"2211.12499","title":"Instant Volumetric Head Avatars","created":"2022-11-22","cited_by_count":159,"area":null},{"id":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103,"area":null},{"id":"2305.08293","title":"Identity-Preserving Talking Face Generation with Landmark and Appearance Priors","created":"2023-05-15","cited_by_count":98,"area":null},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98,"area":null},{"id":"2401.08503","title":"Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis","created":"2024-01-16","cited_by_count":97,"area":null},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88,"area":null},{"id":"2305.04926","title":"RelPose++: Recovering 6D Poses from Sparse-view Observations","created":"2023-05-08","cited_by_count":87,"area":null},{"id":"2504.04842","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","created":"2025-04-07","cited_by_count":77,"area":null},{"id":"2306.15162","title":"YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus","created":"2023-06-27","cited_by_count":75,"area":null},{"id":"2501.06994","title":"Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning","created":"2025-01-13","cited_by_count":59,"area":"offlinerl"},{"id":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59,"area":null},{"id":"2412.09262","title":"LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision","created":"2024-12-12","cited_by_count":56,"area":"diffusion"},{"id":"2404.07991","title":"GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh","created":"2024-04-11","cited_by_count":51,"area":null},{"id":"2412.12861","title":"Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera","created":"2024-12-17","cited_by_count":51,"area":null},{"id":"2312.02702","title":"Neural Sign Actors: A diffusion model for 3D sign language production from text","created":"2023-12-05","cited_by_count":49,"area":"diffusion"},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45,"area":"ssm"},{"id":"2309.06441","title":"Learning Disentangled Avatars with Hybrid 3D Representations","created":"2023-09-12","cited_by_count":44,"area":null},{"id":"2407.18911","title":"HRP: Human Affordances for Robotic Pre-Training","created":"2024-07-26","cited_by_count":44,"area":null},{"id":"2508.08248","title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","created":"2025-08-11","cited_by_count":44,"area":"diffusion"},{"id":"2509.16630","title":"Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation","created":"2025-09-20","cited_by_count":43,"area":null},{"id":"2311.17957","title":"HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting","created":"2023-11-29","cited_by_count":42,"area":"diffusion"},{"id":"2411.19509","title":"Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis","created":"2024-11-29","cited_by_count":41,"area":"diffusion"},{"id":"2304.06371","title":"Sign Language Translation from Instructional Videos","created":"2023-04-13","cited_by_count":39,"area":null},{"id":"2411.12633","title":"Instant Policy: In-Context Imitation Learning via Graph Diffusion","created":"2024-11-19","cited_by_count":39,"area":"offlinerl"},{"id":"2303.07944","title":"Non-Contrastive Unsupervised Learning of Physiological Signals from Video","created":"2023-03-14","cited_by_count":37,"area":null},{"id":"2309.16859","title":"Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis","created":"2023-09-28","cited_by_count":37,"area":null},{"id":"2410.08792","title":"VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model","created":"2024-10-11","cited_by_count":37,"area":"mllm"},{"id":"2402.06149","title":"HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting","created":"2024-02-09","cited_by_count":35,"area":null},{"id":"2304.05934","title":"ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition","created":"2023-04-12","cited_by_count":34,"area":null},{"id":"2410.04221","title":"TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation","created":"2024-10-05","cited_by_count":32,"area":null},{"id":"2505.18096","title":"DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations","created":"2025-05-23","cited_by_count":32,"area":null},{"id":"2401.00847","title":"Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera","created":"2024-01-01","cited_by_count":31,"area":null},{"id":"2301.04474","title":"Speech Driven Video Editing via an Audio-Conditioned Diffusion Model","created":"2023-01-10","cited_by_count":28,"area":"diffusion"},{"id":"2406.00783","title":"AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2406.14272","title":"MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset","created":"2024-06-20","cited_by_count":28,"area":null},{"id":"2507.23143","title":"X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention","created":"2025-07-30","cited_by_count":28,"area":null},{"id":"2209.03277","title":"K-VIL: Keypoints-based Visual Imitation Learning","created":"2022-09-07","cited_by_count":27,"area":"offlinerl"},{"id":"2312.16737","title":"HMP: Hand Motion Priors for Pose and Shape Estimation from Video","created":"2023-12-27","cited_by_count":23,"area":null},{"id":"2312.07539","title":"HeadArtist: Text-conditioned 3D Head Generation with Self Score Distillation","created":"2023-12-12","cited_by_count":22,"area":null},{"id":"2405.07472","title":"GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting","created":"2024-05-13","cited_by_count":22,"area":null},{"id":"2411.16765","title":"SHuBERT: Self-Supervised Sign Language Representation Learning via Multi-Stream Cluster Prediction","created":"2024-11-25","cited_by_count":22,"area":null},{"id":"2412.17812","title":"FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads","created":"2024-12-23","cited_by_count":22,"area":null},{"id":"2505.03351","title":"GUAVA: Generalizable Upper Body 3D Gaussian Avatar","created":"2025-05-06","cited_by_count":22,"area":null},{"id":"2203.12441","title":"M-SENA: An Integrated Platform for Multimodal Sentiment Analysis","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2411.17799","title":"Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator","created":"2024-11-26","cited_by_count":21,"area":null},{"id":"2305.06225","title":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2023-05-10","cited_by_count":20,"area":null},{"id":"2308.13872","title":"Vision-Based Human Pose Estimation via Deep Learning: A Survey","created":"2023-08-26","cited_by_count":20,"area":null},{"id":"2407.01264","title":"SignCLIP: Connecting Text and Sign Language by Contrastive Learning","created":"2024-07-01","cited_by_count":20,"area":null},{"id":"2403.02563","title":"Systemic Biases in Sign Language AI Research: A Deaf-Led Call to Reevaluate Research Agendas","created":"2024-03-05","cited_by_count":19,"area":null},{"id":"2406.06907","title":"SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale","created":"2024-06-11","cited_by_count":19,"area":null},{"id":"2407.08634","title":"RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2210.02755","title":"Audio-Visual Face Reenactment","created":"2022-10-06","cited_by_count":18,"area":null},{"id":"2309.00310","title":"Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture","created":"2023-09-01","cited_by_count":18,"area":null},{"id":"2311.10174","title":"JWSign: A Highly Multilingual Corpus of Bible Translations for more Diversity in Sign Language Processing","created":"2023-11-16","cited_by_count":18,"area":null},{"id":"2104.05043","title":"Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning","created":"2021-04-11","cited_by_count":17,"area":null},{"id":"2108.06038","title":"Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration","created":"2021-08-13","cited_by_count":17,"area":null},{"id":"2404.11499","title":"A Data-Driven Representation for Sign Language Production","created":"2024-04-17","cited_by_count":17,"area":null},{"id":"2504.02542","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","created":"2025-04-03","cited_by_count":17,"area":"diffusion"},{"id":"2308.09525","title":"Improving 3D Pose Estimation for Sign Language","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2308.11198","title":"Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views","created":"2023-08-22","cited_by_count":16,"area":null},{"id":"2401.09386","title":"Tri$^{2}$-plane: Thinking Head Avatar via Feature Pyramid","created":"2024-01-17","cited_by_count":16,"area":null},{"id":"2403.03270","title":"Bi-KVIL: Keypoints-based Visual Imitation Learning of Bimanual Manipulation Tasks","created":"2024-03-05","cited_by_count":16,"area":"offlinerl"},{"id":"2503.18429","title":"Teller: Real-Time Streaming Audio-Driven Portrait Animation with Autoregressive Motion Generation","created":"2025-03-24","cited_by_count":16,"area":null},{"id":"2605.24934","title":"HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos","created":"2026-05-24","cited_by_count":16,"area":null},{"id":"2109.12946","title":"Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks","created":"2021-09-27","cited_by_count":15,"area":null},{"id":"2304.05403","title":"Isolated Sign Language Recognition based on Tree Structure Skeleton Images","created":"2023-04-10","cited_by_count":15,"area":null},{"id":"2409.04033","title":"Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamics","created":"2024-09-06","cited_by_count":15,"area":null},{"id":"2503.10399","title":"HSEmotion Team at ABAW-8 Competition: Audiovisual Ambivalence/Hesitancy, Emotional Mimicry Intensity and Facial Expression Recognition","created":"2025-03-13","cited_by_count":15,"area":null},{"id":"2503.19906","title":"AvatarArtist: Open-Domain 4D Avatarization","created":"2025-03-25","cited_by_count":15,"area":"diffusion"},{"id":"2508.13104","title":"Precise Action-to-Video Generation Through Visual Action Prompts","created":"2025-08-18","cited_by_count":15,"area":null},{"id":"2301.00114","title":"Skeletal Video Anomaly Detection using Deep Learning: Survey, Challenges and Future Directions","created":"2022-12-31","cited_by_count":14,"area":null},{"id":"2503.07499","title":"AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2505.12632","title":"Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents","created":"2025-05-19","cited_by_count":14,"area":"mllm"},{"id":"2304.04437","title":"Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration","created":"2023-04-10","cited_by_count":13,"area":null},{"id":"2403.10731","title":"Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generation","created":"2024-03-15","cited_by_count":13,"area":"diffusion"},{"id":"2408.14975","title":"MegActor-$\\Sigma$: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer","created":"2024-08-27","cited_by_count":13,"area":"diffusion"},{"id":"2507.12956","title":"FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers","created":"2025-07-17","cited_by_count":13,"area":"diffusion"},{"id":"2509.05513","title":"OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous Manipulation","created":"2025-09-05","cited_by_count":13,"area":"offlinerl"},{"id":"2305.00521","title":"StyleLipSync: Style-based Personalized Lip-sync Video Generation","created":"2023-04-30","cited_by_count":12,"area":null},{"id":"2404.13274","title":"Augmented Object Intelligence with XR-Objects","created":"2024-04-20","cited_by_count":12,"area":null},{"id":"2412.14195","title":"A multimodal dataset for understanding the impact of mobile phones on remote online virtual education","created":"2024-12-13","cited_by_count":12,"area":null},{"id":"2501.01808","title":"MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation","created":"2025-01-03","cited_by_count":12,"area":null},{"id":"2506.00129","title":"Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation","created":"2025-05-30","cited_by_count":12,"area":null},{"id":"2106.10882","title":"Affect-driven Ordinal Engagement Measurement from Video","created":"2021-06-21","cited_by_count":11,"area":null},{"id":"2403.09326","title":"HeadEvolver: Text to Head Avatars via Expressive and Attribute-Preserving Mesh Deformation","created":"2024-03-14","cited_by_count":11,"area":null},{"id":"2407.13975","title":"Personalized Privacy Protection Mask Against Unauthorized Facial Recognition","created":"2024-07-19","cited_by_count":11,"area":null},{"id":"2503.21408","title":"VALLR: Visual ASR Language Model for Lip Reading","created":"2025-03-27","cited_by_count":11,"area":null},{"id":"2504.02386","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","created":"2025-04-03","cited_by_count":11,"area":null},{"id":"2108.07917","title":"Classification of Abnormal Hand Movement for Aiding in Autism Detection: Machine Learning Study","created":"2021-08-18","cited_by_count":10,"area":null},{"id":"2204.11820","title":"Real-Time Neural Character Rendering with Pose-Guided Multiplane Images","created":"2022-04-25","cited_by_count":10,"area":null}],"next_cursor":"100"}