{"total":107,"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":"2204.08680","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":"2303.17602","title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","created":"2023-03-30","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":"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":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59,"area":null},{"id":"2203.06541","title":"Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning","created":"2022-03-13","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":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38,"area":null},{"id":"2207.10387","title":"Pose for Everything: Towards Category-Agnostic Pose Estimation","created":"2022-07-21","cited_by_count":36,"area":null},{"id":"2307.16687","title":"DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation","created":"2023-07-31","cited_by_count":36,"area":"diffusion"},{"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":"2210.06110","title":"Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers","created":"2022-10-12","cited_by_count":33,"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":"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":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"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":"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":"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":"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":"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":"2305.19402","title":"Contextual Vision Transformers for Robust Representation Learning","created":"2023-05-30","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":"2210.00740","title":"Heatmap Distribution Matching for Human Pose Estimation","created":"2022-10-03","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":"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":"2304.02939","title":"All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletes","created":"2023-04-06","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":"2303.01503","title":"FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentation","created":"2023-03-02","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":"2408.02285","title":"Joint-Motion Mutual Learning for Pose Estimation in Videos","created":"2024-08-05","cited_by_count":7,"area":null},{"id":"2208.11960","title":"FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2210.04014","title":"AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regression","created":"2022-10-08","cited_by_count":6,"area":null},{"id":"2211.09446","title":"Detecting Arbitrary Keypoints on Limbs and Skis with Sparse Partly Correct Segmentation Masks","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2308.05382","title":"Interaction-aware Joint Attention Estimation Using People Attributes","created":"2023-08-10","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":"2404.10880","title":"HumMUSS: Human Motion Understanding using State Space Models","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2204.06326","title":"Recognition of Freely Selected Keypoints on Human Limbs","created":"2022-04-13","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":"2306.17074","title":"Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation","created":"2023-06-29","cited_by_count":5,"area":"diffusion"},{"id":"2411.01846","title":"KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension","created":"2024-11-04","cited_by_count":5,"area":"mllm"},{"id":"2505.02481","title":"Finger Pose Estimation for Under-screen Fingerprint Sensor","created":"2025-05-05","cited_by_count":5,"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":"2410.03858","title":"Pose Prior Learner: Unsupervised Categorical Prior Learning for Pose Estimation","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2510.11017","title":"High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation","created":"2025-10-13","cited_by_count":4,"area":"ssm"},{"id":"2112.10716","title":"BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations","created":"2021-12-20","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":"2506.05397","title":"Gen4D: Synthesizing Humans and Scenes in the Wild","created":"2025-06-03","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":"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":"2404.10985","title":"Pixel-Wise Symbol Spotting via Progressive Points Location for Parsing CAD Images","created":"2024-04-17","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":"2507.12463","title":"MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2508.17746","title":"DroneKey: Drone 3D Pose Estimation in Image Sequences using Gated Key-representation and Pose-adaptive Learning","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2512.06306","title":"Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2512.20128","title":"milliMamba: Specular-Aware Human Pose Estimation via Dual mmWave Radar with Multi-Frame Mamba Fusion","created":"2025-12-23","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":"2209.01620","title":"MAFormer: A Transformer Network with Multi-scale Attention Fusion for Visual Recognition","created":"2022-08-31","cited_by_count":1,"area":null},{"id":"2304.02994","title":"Visualizing Skiers' Trajectories in Monocular Videos","created":"2023-04-06","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":"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":"2412.01422","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":"2504.10190","title":"Differentially Private 2D Human Pose Estimation","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2505.21309","title":"Spectral Compression Transformer with Line Pose Graph for Monocular 3D Human Pose Estimation","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2202.09115","title":"Towards Simple and Accurate Human Pose Estimation with Stair Network","created":"2022-02-18","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},{"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":"2405.20084","title":"Estimating Human Poses Across Datasets: A Unified Skeleton and Multi-Teacher Distillation Approach","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2408.13646","title":"Mean Height Aided Post-Processing for Pedestrian Detection","created":"2024-08-24","cited_by_count":0,"area":null},{"id":"2409.01555","title":"EA-RAS: Towards Efficient and Accurate End-to-End Reconstruction of Anatomical Skeleton","created":"2024-09-03","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":"2411.13607","title":"VioPose: Violin Performance 4D Pose Estimation by Hierarchical Audiovisual Inference","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2501.11069","title":"Refinement Module based on Parse Graph for Human Pose Estimation","created":"2025-01-19","cited_by_count":0,"area":null},{"id":"2503.00232","title":"Transformers with Joint Tokens and Local-Global Attention for Efficient Human Pose Estimation","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2503.20248","title":"Incremental Object Keypoint Learning","created":"2025-03-26","cited_by_count":0,"area":null}],"next_cursor":"100"}