{"total":1162,"rows":[{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503,"area":"diffusion"},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351,"area":"diffusion"},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485,"area":null},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479,"area":"diffusion"},{"id":"2105.02872","title":"Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies","created":"2021-05-06","cited_by_count":361,"area":null},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354,"area":"diffusion"},{"id":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324,"area":null},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311,"area":null},{"id":"2103.16874","title":"VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization","created":"2021-03-31","cited_by_count":287,"area":null},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257,"area":null},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254,"area":null},{"id":"2103.16507","title":"PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop","created":"2021-03-30","cited_by_count":250,"area":null},{"id":"2102.06199","title":"A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose","created":"2021-02-11","cited_by_count":233,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206,"area":null},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205,"area":null},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200,"area":null},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180,"area":null},{"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,"area":null},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175,"area":null},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175,"area":null},{"id":"2108.07845","title":"ARCH++: Animation-Ready Clothed Human Reconstruction Revisited","created":"2021-08-17","cited_by_count":174,"area":null},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169,"area":null},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167,"area":"diffusion"},{"id":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153,"area":null},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153,"area":null},{"id":"2403.01779","title":"OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on","created":"2024-03-04","cited_by_count":151,"area":"diffusion"},{"id":"2112.07642","title":"EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices","created":"2021-12-14","cited_by_count":139,"area":null},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137,"area":null},{"id":"2302.11566","title":"Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition","created":"2023-02-22","cited_by_count":134,"area":null},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130,"area":null},{"id":"2303.09119","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","created":"2023-03-16","cited_by_count":129,"area":"diffusion"},{"id":"2303.13756","title":"GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning","created":"2023-03-24","cited_by_count":120,"area":null},{"id":"2311.08581","title":"Drivable 3D Gaussian Avatars","created":"2023-11-14","cited_by_count":120,"area":null},{"id":"2311.12052","title":"MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion","created":"2023-11-18","cited_by_count":117,"area":"diffusion"},{"id":"2105.02976","title":"LASR: Learning Articulated Shape Reconstruction from a Monocular Video","created":"2021-05-06","cited_by_count":116,"area":null},{"id":"2204.02569","title":"Gait Recognition in the Wild with Dense 3D Representations and A Benchmark","created":"2022-04-06","cited_by_count":114,"area":null},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107,"area":null},{"id":"2104.14466","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","created":"2021-04-29","cited_by_count":106,"area":null},{"id":"2212.04498","title":"VideoDex: Learning Dexterity from Internet Videos","created":"2022-12-08","cited_by_count":106,"area":null},{"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,"area":null},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103,"area":null},{"id":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103,"area":null},{"id":"2204.08680","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","created":"2022-04-19","cited_by_count":101,"area":null},{"id":"2108.10399","title":"Learning Motion Priors for 4D Human Body Capture in 3D Scenes","created":"2021-08-23","cited_by_count":98,"area":null},{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98,"area":null},{"id":"2308.16894","title":"EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild","created":"2023-08-31","cited_by_count":97,"area":null},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95,"area":null},{"id":"2209.12354","title":"InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction","created":"2022-09-26","cited_by_count":93,"area":null},{"id":"2403.15931","title":"X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention","created":"2024-03-23","cited_by_count":91,"area":"diffusion"},{"id":"2104.00702","title":"NPMs: Neural Parametric Models for 3D Deformable Shapes","created":"2021-04-01","cited_by_count":90,"area":null},{"id":"2112.03590","title":"Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition","created":"2021-12-07","cited_by_count":90,"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":"2207.13807","title":"Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields","created":"2022-07-27","cited_by_count":85,"area":null},{"id":"2205.09443","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","created":"2022-05-19","cited_by_count":83,"area":null},{"id":"2202.10448","title":"Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube","created":"2022-02-21","cited_by_count":82,"area":null},{"id":"2209.09391","title":"QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars","created":"2022-09-20","cited_by_count":77,"area":null},{"id":"2203.15720","title":"Transformer Inertial Poser: Real-time Human Motion Reconstruction from Sparse IMUs with Simultaneous Terrain Generation","created":"2022-03-29","cited_by_count":76,"area":null},{"id":"2306.02898","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","created":"2023-06-05","cited_by_count":75,"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":"2105.01057","title":"Neural Monocular 3D Human Motion Capture with Physical Awareness","created":"2021-05-03","cited_by_count":71,"area":null},{"id":"2105.05222","title":"Including Signed Languages in Natural Language Processing","created":"2021-05-11","cited_by_count":68,"area":null},{"id":"2107.03332","title":"SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation","created":"2021-07-07","cited_by_count":68,"area":null},{"id":"2303.02760","title":"Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes","created":"2023-03-05","cited_by_count":68,"area":null},{"id":"2312.03079","title":"LooseControl: Lifting ControlNet for Generalized Depth Conditioning","created":"2023-12-05","cited_by_count":68,"area":"diffusion"},{"id":"2301.05339","title":"A Comprehensive Review of Data-Driven Co-Speech Gesture Generation","created":"2023-01-13","cited_by_count":66,"area":null},{"id":"2303.04805","title":"X-Avatar: Expressive Human Avatars","created":"2023-03-08","cited_by_count":66,"area":null},{"id":"2103.11703","title":"Model-based 3D Hand Reconstruction via Self-Supervised Learning","created":"2021-03-22","cited_by_count":65,"area":null},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65,"area":null},{"id":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64,"area":null},{"id":"2407.17438","title":"HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation","created":"2024-07-24","cited_by_count":64,"area":null},{"id":"2204.01695","title":"LISA: Learning Implicit Shape and Appearance of Hands","created":"2022-04-04","cited_by_count":63,"area":null},{"id":"2104.08363","title":"StylePeople: A Generative Model of Fullbody Human Avatars","created":"2021-04-16","cited_by_count":62,"area":null},{"id":"2203.15354","title":"Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production","created":"2022-03-29","cited_by_count":61,"area":null},{"id":"2506.22355","title":"Embodied AI Agents: Modeling the World","created":"2025-06-27","cited_by_count":61,"area":"wm"},{"id":"2101.06571","title":"S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling","created":"2021-01-17","cited_by_count":59,"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":"2303.16479","title":"Visibility Aware Human-Object Interaction Tracking from Single RGB Camera","created":"2023-03-29","cited_by_count":58,"area":null},{"id":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57,"area":null},{"id":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57,"area":null},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56,"area":null},{"id":"2204.07855","title":"Towards a Deeper Understanding of Skeleton-based Gait Recognition","created":"2022-04-16","cited_by_count":56,"area":null},{"id":"2410.00086","title":"ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer","created":"2024-09-30","cited_by_count":56,"area":"diffusion"},{"id":"2103.02440","title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","created":"2021-03-03","cited_by_count":55,"area":null},{"id":"2204.06160","title":"Neural Texture Extraction and Distribution for Controllable Person Image Synthesis","created":"2022-04-13","cited_by_count":55,"area":null},{"id":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55,"area":null},{"id":"2104.07021","title":"Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing","created":"2021-04-14","cited_by_count":54,"area":null},{"id":"2304.12518","title":"IMUPoser: Full-Body Pose Estimation using IMUs in Phones, Watches, and Earbuds","created":"2023-04-25","cited_by_count":54,"area":null},{"id":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54,"area":null},{"id":"2304.14406","title":"Putting People in Their Place: Affordance-Aware Human Insertion into Scenes","created":"2023-04-27","cited_by_count":53,"area":null},{"id":"2107.07797","title":"Conditional Directed Graph Convolution for 3D Human Pose Estimation","created":"2021-07-16","cited_by_count":52,"area":null},{"id":"2312.02150","title":"Readout Guidance: Learning Control from Diffusion Features","created":"2023-12-04","cited_by_count":52,"area":"diffusion"},{"id":"2103.06982","title":"Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks","created":"2021-03-11","cited_by_count":50,"area":null},{"id":"2107.11317","title":"Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives","created":"2021-07-23","cited_by_count":50,"area":null},{"id":"2206.07036","title":"Accurate 3D Body Shape Regression using Metric and Semantic Attributes","created":"2022-06-14","cited_by_count":50,"area":null},{"id":"2304.05690","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","created":"2023-04-12","cited_by_count":49,"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":"2104.05485","title":"Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention","created":"2021-04-12","cited_by_count":48,"area":null},{"id":"2303.14747","title":"Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation","created":"2023-03-26","cited_by_count":47,"area":null},{"id":"2307.05853","title":"GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video","created":"2023-07-12","cited_by_count":47,"area":null}],"next_cursor":"100"}