{"total":1064,"rows":[{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961,"area":"diffusion"},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688,"area":"diffusion"},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668,"area":"lr"},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359,"area":"diffusion"},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330,"area":"diffusion"},{"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":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272,"area":null},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272,"area":"diffusion"},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257,"area":null},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227,"area":null},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210,"area":null},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"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":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200,"area":"diffusion"},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193,"area":null},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180,"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":"2204.08532","title":"Dress Code: High-Resolution Multi-Category Virtual Try-On","created":"2022-04-18","cited_by_count":162,"area":null},{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159,"area":null},{"id":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155,"area":null},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152,"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":"2204.11823","title":"StyleGAN-Human: A Data-Centric Odyssey of Human Generation","created":"2022-04-25","cited_by_count":144,"area":null},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142,"area":null},{"id":"2104.07267","title":"ContactOpt: Optimizing Contact to Improve Grasps","created":"2021-04-15","cited_by_count":139,"area":null},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131,"area":null},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124,"area":null},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124,"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":"2104.00683","title":"SimPoE: Simulated Character Control for 3D Human Pose Estimation","created":"2021-04-01","cited_by_count":114,"area":null},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112,"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":"2304.04269","title":"HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation","created":"2023-04-09","cited_by_count":105,"area":"diffusion"},{"id":"2211.12500","title":"Person Image Synthesis via Denoising Diffusion Model","created":"2022-11-22","cited_by_count":104,"area":"diffusion"},{"id":"2310.06313","title":"Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models","created":"2023-10-10","cited_by_count":104,"area":"diffusion"},{"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":"2407.12705","title":"IMAGDressing-v1: Customizable Virtual Dressing","created":"2024-07-17","cited_by_count":100,"area":"diffusion"},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99,"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":"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":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96,"area":null},{"id":"1905.13566","title":"Recent Advances in Imitation Learning from Observation","created":"2019-05-30","cited_by_count":93,"area":"offlinerl"},{"id":"2312.07536","title":"FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition","created":"2023-12-12","cited_by_count":91,"area":"diffusion"},{"id":"2204.01046","title":"Style-Based Global Appearance Flow for Virtual Try-On","created":"2022-04-03","cited_by_count":88,"area":null},{"id":"2106.15125","title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","created":"2021-06-29","cited_by_count":87,"area":null},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87,"area":null},{"id":"2208.10741","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2022-08-23","cited_by_count":85,"area":null},{"id":"2303.11579","title":"Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation","created":"2023-03-21","cited_by_count":82,"area":null},{"id":"2205.04992","title":"KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints","created":"2022-05-10","cited_by_count":77,"area":null},{"id":"2308.14749","title":"MagicEdit: High-Fidelity and Temporally Coherent Video Editing","created":"2023-08-28","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":"2105.01057","title":"Neural Monocular 3D Human Motion Capture with Physical Awareness","created":"2021-05-03","cited_by_count":71,"area":null},{"id":"2206.13028","title":"Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition","created":"2022-06-27","cited_by_count":71,"area":null},{"id":"2303.15108","title":"High-fidelity 3D Human Digitization from Single 2K Resolution Images","created":"2023-03-27","cited_by_count":70,"area":null},{"id":"2312.03461","title":"HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting","created":"2023-12-06","cited_by_count":70,"area":null},{"id":"2312.02087","title":"VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence","created":"2023-12-04","cited_by_count":69,"area":"diffusion"},{"id":"2112.02466","title":"Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer","created":"2021-12-05","cited_by_count":68,"area":null},{"id":"2203.02910","title":"Exploring Dual-task Correlation for Pose Guided Person Image Generation","created":"2022-03-06","cited_by_count":68,"area":null},{"id":"2204.06806","title":"YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss","created":"2022-04-14","cited_by_count":68,"area":null},{"id":"2212.07626","title":"NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions","created":"2022-12-15","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":"2404.09967","title":"Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model","created":"2024-04-15","cited_by_count":66,"area":"diffusion"},{"id":"2104.07300","title":"Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes","created":"2021-04-15","cited_by_count":65,"area":null},{"id":"2105.13680","title":"Focus on Local: Detecting Lane Marker from Bottom Up via Key Point","created":"2021-05-28","cited_by_count":65,"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":"2107.00285","title":"iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis","created":"2021-07-01","cited_by_count":63,"area":null},{"id":"2103.04023","title":"PISE: Person Image Synthesis and Editing with Decoupled GAN","created":"2021-03-06","cited_by_count":62,"area":null},{"id":"2109.02303","title":"Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation","created":"2021-09-06","cited_by_count":62,"area":null},{"id":"2203.08534","title":"Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video","created":"2022-03-16","cited_by_count":60,"area":null},{"id":"2308.00906","title":"ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation","created":"2023-08-02","cited_by_count":59,"area":null},{"id":"2402.13251","title":"FlashTex: Fast Relightable Mesh Texturing with LightControlNet","created":"2024-02-20","cited_by_count":56,"area":null},{"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":"2108.02092","title":"Online Knowledge Distillation for Efficient Pose Estimation","created":"2021-08-04","cited_by_count":55,"area":"distill"},{"id":"2102.09546","title":"Deep Gait Recognition: A Survey","created":"2021-02-18","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":"2312.02963","title":"MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures","created":"2023-12-05","cited_by_count":54,"area":null},{"id":"2103.07254","title":"Deep Dual Consecutive Network for Human Pose Estimation","created":"2021-03-12","cited_by_count":51,"area":null},{"id":"2107.00646","title":"Learning to See before Learning to Act: Visual Pre-training for Manipulation","created":"2021-07-01","cited_by_count":51,"area":null},{"id":"2104.11536","title":"Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective","created":"2021-04-23","cited_by_count":50,"area":null},{"id":"2102.05150","title":"RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2402.04857","title":"Advancing Video Anomaly Detection: A Concise Review and a New Dataset","created":"2024-02-07","cited_by_count":49,"area":null},{"id":"2302.01593","title":"Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation","created":"2023-02-03","cited_by_count":48,"area":null},{"id":"2401.08570","title":"RoHM: Robust Human Motion Reconstruction via Diffusion","created":"2024-01-16","cited_by_count":48,"area":null},{"id":"2402.18078","title":"Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis","created":"2024-02-28","cited_by_count":48,"area":"diffusion"},{"id":"2104.00340","title":"Reconstructing 3D Human Pose by Watching Humans in the Mirror","created":"2021-04-01","cited_by_count":47,"area":null},{"id":"2308.11184","title":"ReFit: Recurrent Fitting Network for 3D Human Recovery","created":"2023-08-22","cited_by_count":47,"area":null},{"id":"2403.09508","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","created":"2024-03-14","cited_by_count":47,"area":null},{"id":"2303.03301","title":"Exploring Deep Models for Practical Gait Recognition","created":"2023-03-06","cited_by_count":46,"area":null},{"id":"2105.02467","title":"Body Meshes as Points","created":"2021-05-06","cited_by_count":45,"area":null},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2402.19122","title":"BigGait: Learning Gait Representation You Want by Large Vision Models","created":"2024-02-29","cited_by_count":45,"area":null},{"id":"2104.06650","title":"Learning Semantic Person Image Generation by Region-Adaptive Normalization","created":"2021-04-14","cited_by_count":44,"area":null},{"id":"2206.07771","title":"Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation","created":"2022-06-15","cited_by_count":44,"area":"diffusion"},{"id":"2306.05872","title":"Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction","created":"2023-06-09","cited_by_count":43,"area":null}],"next_cursor":"100"}