{"total":121,"rows":[{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350,"area":null},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287,"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":"2104.02699","title":"ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement","created":"2021-04-06","cited_by_count":248,"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":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131,"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":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99,"area":null},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74,"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":"2104.00622","title":"RGB-D Local Implicit Function for Depth Completion of Transparent Objects","created":"2021-04-01","cited_by_count":64,"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":"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":"2308.11184","title":"ReFit: Recurrent Fitting Network for 3D Human Recovery","created":"2023-08-22","cited_by_count":47,"area":null},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2201.07412","title":"Poseur: Direct Human Pose Regression with Transformers","created":"2022-01-19","cited_by_count":43,"area":null},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42,"area":null},{"id":"2107.02133","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","created":"2021-07-05","cited_by_count":33,"area":null},{"id":"2409.19405","title":"G3R: Gradient Guided Generalizable Reconstruction","created":"2024-09-28","cited_by_count":31,"area":null},{"id":"2307.04751","title":"Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement","created":"2023-07-10","cited_by_count":29,"area":null},{"id":"2404.04430","title":"PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos","created":"2024-04-05","cited_by_count":28,"area":null},{"id":"2112.06183","title":"Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species","created":"2021-12-12","cited_by_count":27,"area":null},{"id":"2105.04154","title":"Unsupervised Human Pose Estimation through Transforming Shape Templates","created":"2021-05-10","cited_by_count":26,"area":null},{"id":"2203.11832","title":"Cross-View Panorama Image Synthesis","created":"2022-03-22","cited_by_count":26,"area":null},{"id":"2206.04511","title":"Efficient Human Pose Estimation via 3D Event Point Cloud","created":"2022-06-09","cited_by_count":25,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2107.12090","title":"Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition","created":"2021-07-26","cited_by_count":24,"area":null},{"id":"2108.08557","title":"DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders","created":"2021-08-19","cited_by_count":23,"area":null},{"id":"2211.15692","title":"H3WB: Human3.6M 3D WholeBody Dataset and Benchmark","created":"2022-11-28","cited_by_count":23,"area":null},{"id":"2204.07370","title":"2D Human Pose Estimation: A Survey","created":"2022-04-15","cited_by_count":21,"area":null},{"id":"2105.09936","title":"BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Image","created":"2021-05-20","cited_by_count":20,"area":null},{"id":"2109.14335","title":"A Systematic Survey of Deep Learning-based Single-Image Super-Resolution","created":"2021-09-29","cited_by_count":19,"area":null},{"id":"2510.16258","title":"Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset","created":"2025-10-17","cited_by_count":19,"area":null},{"id":"2109.09150","title":"A Study of the Generalizability of Self-Supervised Representations","created":"2021-09-19","cited_by_count":18,"area":null},{"id":"2406.04659","title":"LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model","created":"2024-06-07","cited_by_count":17,"area":null},{"id":"2408.00672","title":"ExpertAF: Expert Actionable Feedback from Video","created":"2024-08-01","cited_by_count":17,"area":null},{"id":"2309.13692","title":"Regularization and Optimal Multiclass Learning","created":"2023-09-24","cited_by_count":15,"area":null},{"id":"2412.09601","title":"TimeRefine: Temporal Grounding with Time Refining Video LLM","created":"2024-12-12","cited_by_count":15,"area":null},{"id":"2212.01055","title":"Transformer-Based Learned Optimization","created":"2022-12-02","cited_by_count":13,"area":null},{"id":"2107.12081","title":"Towards the Unseen: Iterative Text Recognition by Distilling from Errors","created":"2021-07-26","cited_by_count":12,"area":null},{"id":"2502.19402","title":"General Intelligence Requires Reward-based Pretraining","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2101.07719","title":"Deep Feedback Inverse Problem Solver","created":"2021-01-19","cited_by_count":11,"area":null},{"id":"2403.16732","title":"Enabling Uncertainty Estimation in Iterative Neural Networks","created":"2024-03-25","cited_by_count":11,"area":null},{"id":"2502.09617","title":"LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2301.06020","title":"Delving Deep into Pixel Alignment Feature for Accurate Multi-view Human Mesh Recovery","created":"2023-01-15","cited_by_count":10,"area":null},{"id":"2309.15762","title":"Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback","created":"2023-09-27","cited_by_count":10,"area":null},{"id":"2201.07384","title":"Swin-Pose: Swin Transformer Based Human Pose Estimation","created":"2022-01-19","cited_by_count":9,"area":null},{"id":"2210.00740","title":"Heatmap Distribution Matching for Human Pose Estimation","created":"2022-10-03","cited_by_count":9,"area":null},{"id":"2212.12910","title":"Learning to Estimate 3D Human Pose from Point Cloud","created":"2022-12-25","cited_by_count":9,"area":null},{"id":"2308.02177","title":"Scene-aware Human Pose Generation using Transformer","created":"2023-08-04","cited_by_count":9,"area":null},{"id":"2103.15534","title":"An Adversarial Human Pose Estimation Network Injected with Graph Structure","created":"2021-03-29","cited_by_count":8,"area":null},{"id":"2308.00799","title":"Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction","created":"2023-08-01","cited_by_count":8,"area":null},{"id":"2409.19899","title":"OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2204.05864","title":"Semantic keypoint-based pose estimation from single RGB frames","created":"2022-04-12","cited_by_count":7,"area":null},{"id":"2303.11180","title":"Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2307.16765","title":"Lightweight Super-Resolution Head for Human Pose Estimation","created":"2023-07-31","cited_by_count":7,"area":null},{"id":"2103.09754","title":"Diversified Multiscale Graph Learning with Graph Self-Correction","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2310.13039","title":"Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2107.07110","title":"Compact and Optimal Deep Learning with Recurrent Parameter Generators","created":"2021-07-15","cited_by_count":5,"area":null},{"id":"2305.13765","title":"Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2407.12307","title":"Weakly-Supervised 3D Hand Reconstruction with Knowledge Prior and Uncertainty Guidance","created":"2024-07-17","cited_by_count":5,"area":null},{"id":"2408.02713","title":"A Review on Organ Deformation Modeling Approaches for Reliable Surgical Navigation using Augmented Reality","created":"2024-08-05","cited_by_count":5,"area":null},{"id":"2109.10056","title":"Single Person Pose Estimation: A Survey","created":"2021-09-21","cited_by_count":4,"area":null},{"id":"2406.19290","title":"Human Modelling and Pose Estimation Overview","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2503.19207","title":"FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2106.05616","title":"SVMAC: Unsupervised 3D Human Pose Estimation from a Single Image with Single-view-multi-angle Consistency","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2106.06966","title":"Feedback Pyramid Attention Networks for Single Image Super-Resolution","created":"2021-06-13","cited_by_count":3,"area":null},{"id":"2107.12847","title":"Learning Local Recurrent Models for Human Mesh Recovery","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2202.02656","title":"A survey of top-down approaches for human pose estimation","created":"2022-02-05","cited_by_count":3,"area":null},{"id":"2301.10431","title":"Bias-Compensated Integral Regression for Human Pose Estimation","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2310.18920","title":"Improving Multi-Person Pose Tracking with A Confidence Network","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2311.00455","title":"Progressive Recurrent Network for Shadow Removal","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2102.04780","title":"Diverse Single Image Generation with Controllable Global Structure","created":"2021-02-09","cited_by_count":2,"area":null},{"id":"2108.10515","title":"ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones","created":"2021-08-24","cited_by_count":2,"area":null},{"id":"2111.10296","title":"Probabilistic Regression with Huber Distributions","created":"2021-11-19","cited_by_count":2,"area":null},{"id":"2210.05130","title":"ACRNet: Attention Cube Regression Network for Multi-view Real-time 3D Human Pose Estimation in Telemedicine","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2301.07583","title":"A Survey of Advanced Computer Vision Techniques for Sports","created":"2023-01-18","cited_by_count":2,"area":null},{"id":"2409.01879","title":"SPiKE: 3D Human Pose from Point Cloud Sequences","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2505.18342","title":"Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2103.04354","title":"Feedback Refined Local-Global Network for Super-Resolution of Hyperspectral Imagery","created":"2021-03-07","cited_by_count":1,"area":null},{"id":"2105.10904","title":"Skeleton-aware multi-scale heatmap regression for 2D hand pose estimation","created":"2021-05-23","cited_by_count":1,"area":null},{"id":"2106.04274","title":"3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training","created":"2021-06-08","cited_by_count":1,"area":null},{"id":"2203.10373","title":"A naive method to discover directions in the StyleGAN2 latent space","created":"2022-03-19","cited_by_count":1,"area":null},{"id":"2306.03538","title":"SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2307.05896","title":"Deep learning-based estimation of whole-body kinematics from multi-view images","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2309.07513","title":"RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement","created":"2023-09-14","cited_by_count":1,"area":null},{"id":"2405.13999","title":"Computer-Vision-Enabled Worker Video Analysis for Motion Amount Quantification","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2411.18944","title":"Waterfall Transformer for Multi-person Pose Estimation","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2412.01422","title":"MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection","created":"2024-12-02","cited_by_count":1,"area":"ssm"},{"id":"2412.13010","title":"Measurement of Medial Elbow Joint Space using Landmark Detection","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2501.13073","title":"CHaRM: Conditioned Heatmap Regression Methodology for Accurate and Fast Dental Landmark Localization","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2511.19326","title":"MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2102.07318","title":"A Global to Local Double Embedding Method for Multi-person Pose Estimation","created":"2021-02-15","cited_by_count":0,"area":null},{"id":"2105.07245","title":"Composite Localization for Human Pose Estimation","created":"2021-05-15","cited_by_count":0,"area":null},{"id":"2107.03640","title":"A Dataset and Method for Hallux Valgus Angle Estimation Based on Deep Learing","created":"2021-07-08","cited_by_count":0,"area":null},{"id":"2110.10734","title":"Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimation","created":"2021-10-20","cited_by_count":0,"area":null},{"id":"2112.01609","title":"Probabilistic Tracking with Deep Factors","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2204.11535","title":"Combining Visual Saliency Methods and Sparse Keypoint Annotations to Providently Detect Vehicles at Night","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2207.12967","title":"TransFiner: A Full-Scale Refinement Approach for Multiple Object Tracking","created":"2022-07-26","cited_by_count":0,"area":null}],"next_cursor":"100"}