{"total":121,"rows":[{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456,"area":null},{"id":"2111.14813","title":"TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions","created":"2021-11-29","cited_by_count":244,"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":"2111.07910","title":"Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction","created":"2021-11-15","cited_by_count":110,"area":null},{"id":"2203.14564","title":"HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network","created":"2022-03-28","cited_by_count":96,"area":null},{"id":"2204.07908","title":"MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction","created":"2022-04-17","cited_by_count":72,"area":null},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70,"area":null},{"id":"2205.10102","title":"Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging","created":"2022-05-20","cited_by_count":66,"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":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59,"area":null},{"id":"2305.03210","title":"AttentionViz: A Global View of Transformer Attention","created":"2023-05-04","cited_by_count":50,"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":"2203.07436","title":"SuperAnimal pretrained pose estimation models for behavioral analysis","created":"2022-03-14","cited_by_count":39,"area":null},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38,"area":null},{"id":"2312.07526","title":"RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2310.20695","title":"HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception","created":"2023-10-31","cited_by_count":33,"area":null},{"id":"2208.10808","title":"Towards Accurate Facial Landmark Detection via Cascaded Transformers","created":"2022-08-23","cited_by_count":31,"area":null},{"id":"2209.08194","title":"PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation","created":"2022-09-16","cited_by_count":27,"area":null},{"id":"2112.14087","title":"APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers","created":"2021-12-28","cited_by_count":24,"area":null},{"id":"2201.00466","title":"RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmark","created":"2022-01-03","cited_by_count":24,"area":null},{"id":"2304.06133","title":"Towards Evaluating Explanations of Vision Transformers for Medical Imaging","created":"2023-04-12","cited_by_count":23,"area":null},{"id":"2111.08557","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","created":"2021-11-16","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":"2303.08450","title":"PoseRAC: Pose Saliency Transformer for Repetitive Action Counting","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2303.08475","title":"Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2311.17891","title":"A Graph-Based Approach for Category-Agnostic Pose Estimation","created":"2023-11-29","cited_by_count":17,"area":null},{"id":"2312.01061","title":"Spectral-wise Implicit Neural Representation for Hyperspectral Image Reconstruction","created":"2023-12-02","cited_by_count":17,"area":null},{"id":"2303.07840","title":"Precise Facial Landmark Detection by Reference Heatmap Transformer","created":"2023-03-14","cited_by_count":16,"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":"2205.05277","title":"AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation","created":"2022-05-11","cited_by_count":13,"area":null},{"id":"2306.07879","title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","created":"2023-06-13","cited_by_count":13,"area":null},{"id":"2206.11215","title":"Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Training","created":"2022-06-22","cited_by_count":12,"area":null},{"id":"2210.17424","title":"Tree Detection and Diameter Estimation Based on Deep Learning","created":"2022-10-31","cited_by_count":12,"area":null},{"id":"2303.02455","title":"DistilPose: Tokenized Pose Regression with Heatmap Distillation","created":"2023-03-04","cited_by_count":12,"area":null},{"id":"2407.11321","title":"TCFormer: Visual Recognition via Token Clustering Transformer","created":"2024-07-16","cited_by_count":12,"area":null},{"id":"2312.10758","title":"SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation","created":"2023-12-17","cited_by_count":11,"area":null},{"id":"2207.09725","title":"OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos","created":"2022-07-20","cited_by_count":10,"area":null},{"id":"2403.19926","title":"Video-Based Human Pose Regression via Decoupled Space-Time Aggregation","created":"2024-03-29","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":"2205.15448","title":"FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER","created":"2022-05-30","cited_by_count":9,"area":null},{"id":"2301.07322","title":"HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation","created":"2023-01-18","cited_by_count":9,"area":null},{"id":"2304.07916","title":"GaitRef: Gait Recognition with Refined Sequential Skeletons","created":"2023-04-16","cited_by_count":9,"area":null},{"id":"2401.12743","title":"Correlation-Embedded Transformer Tracking: A Single-Branch Framework","created":"2024-01-23","cited_by_count":9,"area":null},{"id":"2406.00384","title":"CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation","created":"2024-06-01","cited_by_count":9,"area":null},{"id":"2207.11972","title":"TransCL: Transformer Makes Strong and Flexible Compressive Learning","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2209.14024","title":"Motion Transformer for Unsupervised Image Animation","created":"2022-09-28","cited_by_count":8,"area":null},{"id":"2303.00298","title":"Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens","created":"2023-03-01","cited_by_count":8,"area":null},{"id":"2312.15612","title":"APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond","created":"2023-12-25","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":"2410.19769","title":"Real-time Monitoring of Lower Limb Movement Resistance Based on Deep Learning","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2112.04981","title":"PE-former: Pose Estimation Transformer","created":"2021-12-09","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":"2206.10892","title":"I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation","created":"2022-06-22","cited_by_count":6,"area":null},{"id":"2208.03431","title":"IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation","created":"2022-08-06","cited_by_count":6,"area":null},{"id":"2210.00662","title":"Under the Cover Infant Pose Estimation using Multimodal Data","created":"2022-10-03","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":"2407.10756","title":"GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2410.22857","title":"DAVINCI: A Single-Stage Architecture for Constrained CAD Sketch Inference","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2107.14633","title":"Video Based Fall Detection Using Human Poses","created":"2021-07-29","cited_by_count":5,"area":null},{"id":"2305.04047","title":"Degradation-Noise-Aware Deep Unfolding Transformer for Hyperspectral Image Denoising","created":"2023-05-06","cited_by_count":5,"area":null},{"id":"2411.07167","title":"Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection","created":"2024-11-08","cited_by_count":5,"area":null},{"id":"2510.15338","title":"Proto-Former: Unified Facial Landmark Detection by Prototype Transformer","created":"2025-10-17","cited_by_count":5,"area":null},{"id":"2210.13053","title":"Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers","created":"2022-10-24","cited_by_count":4,"area":null},{"id":"2211.14703","title":"Exploring Consistency in Cross-Domain Transformer for Domain Adaptive Semantic Segmentation","created":"2022-11-27","cited_by_count":4,"area":null},{"id":"2211.15868","title":"Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2306.04225","title":"Efficient Vision Transformer for Human Pose Estimation via Patch Selection","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2406.14367","title":"PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2411.12301","title":"Physics-Guided Detector for SAR Airplanes","created":"2024-11-19","cited_by_count":4,"area":null},{"id":"2206.02087","title":"Accurate Scoliosis Vertebral Landmark Localization on X-ray Images via Shape-constrained Multi-stage Cascaded CNNs","created":"2022-06-05","cited_by_count":3,"area":null},{"id":"2207.05845","title":"Learning to Estimate External Forces of Human Motion in Video","created":"2022-07-12","cited_by_count":3,"area":null},{"id":"2209.02431","title":"DPIT: Dual-Pipeline Integrated Transformer for Human Pose Estimation","created":"2022-09-02","cited_by_count":3,"area":null},{"id":"2410.09885","title":"Occluded Human Pose Estimation based on Limb Joint Augmentation","created":"2024-10-13","cited_by_count":3,"area":null},{"id":"2502.18214","title":"Learning Structure-Supporting Dependencies via Keypoint Interactive Transformer for General Mammal Pose Estimation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2503.16120","title":"Probabilistic Prompt Distribution Learning for Animal Pose Estimation","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2111.12892","title":"Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2302.10602","title":"SU-Net: Pose estimation network for non-cooperative spacecraft on-orbit","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2307.01004","title":"Joint Coordinate Regression and Association For Multi-Person Pose Estimation, A Pure Neural Network Approach","created":"2023-07-03","cited_by_count":2,"area":null},{"id":"2312.17106","title":"Geometry-Biased Transformer for Robust Multi-View 3D Human Pose Reconstruction","created":"2023-12-28","cited_by_count":2,"area":null},{"id":"2402.08923","title":"IMUOptimize: A Data-Driven Approach to Optimal IMU Placement for Human Pose Estimation with Transformer Architecture","created":"2024-02-14","cited_by_count":2,"area":null},{"id":"2402.18196","title":"NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2409.02715","title":"Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach","created":"2024-09-01","cited_by_count":2,"area":null},{"id":"2410.09312","title":"Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2202.02310","title":"EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2205.12619","title":"Location-free Human Pose Estimation","created":"2022-05-25","cited_by_count":1,"area":null},{"id":"2308.12600","title":"PoseSync: Robust pose based video synchronization","created":"2023-08-24","cited_by_count":1,"area":null},{"id":"2401.16700","title":"Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2404.02345","title":"GaitSTR: Gait Recognition with Sequential Two-stream Refinement","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2406.19726","title":"EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans","created":"2024-06-28","cited_by_count":1,"area":null},{"id":"2409.07752","title":"GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolution","created":"2024-09-12","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":"2412.13010","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":"2503.13344","title":"STEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2603.09418","title":"CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2201.11808","title":"LAP: An Attention-Based Module for Concept Based Self-Interpretation and Knowledge Injection in Convolutional Neural Networks","created":"2022-01-27","cited_by_count":0,"area":null},{"id":"2204.10209","title":"BTranspose: Bottleneck Transformers for Human Pose Estimation with Self-Supervised Pre-Training","created":"2022-04-21","cited_by_count":0,"area":null},{"id":"2304.05548","title":"Distilling Token-Pruned Pose Transformer for 2D Human Pose Estimation","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2311.09653","title":"Improved TokenPose with Sparsity","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2402.11566","title":"Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training","created":"2024-02-18","cited_by_count":0,"area":null}],"next_cursor":"100"}