{"total":99,"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":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206,"area":null},{"id":"2308.05736","title":"MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction","created":"2023-08-10","cited_by_count":193,"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":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150,"area":null},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149,"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":"2204.07908","title":"MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction","created":"2022-04-17","cited_by_count":72,"area":null},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","cited_by_count":70,"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":"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":"2111.12073","title":"Multi-Person 3D Motion Prediction with Multi-Range Transformers","created":"2021-11-23","cited_by_count":63,"area":null},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50,"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":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2201.01893","title":"Flow-Guided Sparse Transformer for Video Deblurring","created":"2022-01-06","cited_by_count":43,"area":null},{"id":"2201.07412","title":"Poseur: Direct Human Pose Regression with Transformers","created":"2022-01-19","cited_by_count":43,"area":null},{"id":"2203.08566","title":"EDTER: Edge Detection with Transformer","created":"2022-03-16","cited_by_count":36,"area":null},{"id":"2205.14354","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","created":"2022-05-28","cited_by_count":34,"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":"2312.04424","title":"Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views","created":"2023-12-07","cited_by_count":33,"area":null},{"id":"2110.09554","title":"TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation","created":"2021-10-18","cited_by_count":32,"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":"2201.06618","title":"VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer","created":"2022-01-17","cited_by_count":27,"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":"2308.07313","title":"Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation","created":"2023-08-14","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":"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":"2204.07370","title":"2D Human Pose Estimation: A Survey","created":"2022-04-15","cited_by_count":21,"area":null},{"id":"2310.08530","title":"X-Pose: Detecting Any Keypoints","created":"2023-10-12","cited_by_count":21,"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":"2110.08994","title":"CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2309.16634","title":"End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon","created":"2023-09-28","cited_by_count":16,"area":null},{"id":"2109.03622","title":"Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation","created":"2021-09-08","cited_by_count":14,"area":null},{"id":"2111.11535","title":"Ice hockey player identification via transformers and weakly supervised learning","created":"2021-11-22","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":"2212.07855","title":"QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Query","created":"2022-12-15","cited_by_count":13,"area":null},{"id":"2203.04907","title":"KPE: Keypoint Pose Encoding for Transformer-based Image Generation","created":"2022-03-09","cited_by_count":12,"area":null},{"id":"2209.13948","title":"Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks","created":"2022-09-28","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":"2308.10174","title":"Neural Interactive Keypoint Detection","created":"2023-08-20","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":"2208.11356","title":"Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2311.17105","title":"On the Calibration of Human Pose Estimation","created":"2023-11-28","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":"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":"2304.07916","title":"GaitRef: Gait Recognition with Refined Sequential Skeletons","created":"2023-04-16","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":"2312.05525","title":"You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2207.01600","title":"CRFormer: A Cross-Region Transformer for Shadow Removal","created":"2022-07-04","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":"2308.08370","title":"Agglomerative Transformer for Human-Object Interaction Detection","created":"2023-08-16","cited_by_count":8,"area":null},{"id":"2309.01010","title":"Mitigating Motion Blur for Robust 3D Baseball Player Pose Modeling for Pitch Analysis","created":"2023-09-02","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":"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":"2207.02976","title":"Semi-supervised Human Pose Estimation in Art-historical Images","created":"2022-07-06","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":"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":"2410.20508","title":"Referring Human Pose and Mask Estimation in the Wild","created":"2024-10-27","cited_by_count":6,"area":null},{"id":"2208.14657","title":"EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud Computing","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2301.06187","title":"CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey","created":"2023-01-15","cited_by_count":4,"area":null},{"id":"2307.11934","title":"LAMP: Leveraging Language Prompts for Multi-person Pose Estimation","created":"2023-07-21","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":"2205.12602","title":"VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation","created":"2022-05-25","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":"2301.10431","title":"Bias-Compensated Integral Regression for Human Pose Estimation","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2309.16189","title":"Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing","created":"2023-09-28","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":"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":"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":"2404.14025","title":"DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation","created":"2024-04-22","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":"2505.02287","title":"Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation","created":"2025-05-04","cited_by_count":2,"area":null},{"id":"2512.06657","title":"TextMamba: Scene Text Detector with Mamba","created":"2025-12-07","cited_by_count":2,"area":"ssm"},{"id":"2205.12619","title":"Location-free Human Pose Estimation","created":"2022-05-25","cited_by_count":1,"area":null},{"id":"2212.03434","title":"Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer","created":"2022-12-07","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":"2404.03518","title":"SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation","created":"2024-04-04","cited_by_count":1,"area":"distill"},{"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":"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":"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":"2505.01837","title":"CVVNet: A Cross-Vertical-View Network for Gait Recognition","created":"2025-05-03","cited_by_count":1,"area":null},{"id":"2605.23507","title":"MDS-DETR: DETR with Masked Duplicate Suppressor","created":"2026-05-22","cited_by_count":1,"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":"2404.01194","title":"Adaptive Query Prompting for Multi-Domain Landmark Detection","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2405.11448","title":"Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation","created":"2024-05-19","cited_by_count":0,"area":"distill"},{"id":"2405.12247","title":"Focus on Low-Resolution Information: Multi-Granular Information-Lossless Model for Low-Resolution Human Pose Estimation","created":"2024-05-19","cited_by_count":0,"area":null},{"id":"2409.07798","title":"GateAttentionPose: Enhancing Pose Estimation with Agent Attention and Improved Gated Convolutions","created":"2024-09-12","cited_by_count":0,"area":null},{"id":"2410.03174","title":"Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2410.22079","title":"HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2501.08408","title":"Leveraging 2D Masked Reconstruction for Domain Adaptation of 3D Pose Estimation","created":"2025-01-14","cited_by_count":0,"area":null},{"id":"2502.13637","title":"Exploring Mutual Cross-Modal Attention for Context-Aware Human Affordance Generation","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2503.20248","title":"Incremental Object Keypoint Learning","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2504.01298","title":"Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2506.05420","title":"Self-supervised One-Stage Learning for RF-based Multi-Person Pose Estimation","created":"2025-06-05","cited_by_count":0,"area":null}],"next_cursor":null}