{"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":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205,"area":null},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155,"area":null},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142,"area":null},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123,"area":null},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"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":"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":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65,"area":null},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60,"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":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56,"area":null},{"id":"2203.13349","title":"Occluded Human Mesh Recovery","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45,"area":null},{"id":"2105.06152","title":"When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks","created":"2021-05-13","cited_by_count":41,"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":"2501.09782","title":"SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation","created":"2025-01-16","cited_by_count":32,"area":null},{"id":"2103.04570","title":"Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing","created":"2021-03-08","cited_by_count":31,"area":null},{"id":"2107.11646","title":"Hand Image Understanding via Deep Multi-Task Learning","created":"2021-07-24","cited_by_count":31,"area":null},{"id":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31,"area":null},{"id":"2101.11223","title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","created":"2021-01-27","cited_by_count":30,"area":null},{"id":"2209.10529","title":"Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms","created":"2022-09-21","cited_by_count":28,"area":null},{"id":"2303.15410","title":"Human Pose Estimation in Extremely Low-Light Conditions","created":"2023-03-27","cited_by_count":27,"area":null},{"id":"2407.06937","title":"HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance","created":"2024-07-09","cited_by_count":25,"area":"diffusion"},{"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":"2404.01424","title":"DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery","created":"2024-04-01","cited_by_count":17,"area":"diffusion"},{"id":"2207.05025","title":"PSP-HDRI$+$: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Models","created":"2022-07-11","cited_by_count":15,"area":null},{"id":"2405.12070","title":"AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements","created":"2024-05-20","cited_by_count":15,"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":"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":"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":"2407.11464","title":"Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes","created":"2024-07-16","cited_by_count":13,"area":null},{"id":"2109.15068","title":"iShape: A First Step Towards Irregular Shape Instance Segmentation","created":"2021-09-30","cited_by_count":12,"area":null},{"id":"2307.16377","title":"JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery","created":"2023-07-31","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":"2411.13842","title":"Detecting Human Artifacts from Text-to-Image Models","created":"2024-11-21","cited_by_count":12,"area":null},{"id":"2504.09480","title":"Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation","created":"2025-04-13","cited_by_count":10,"area":"mllm"},{"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":"2412.02254","title":"ProbPose: A Probabilistic Approach to 2D Human Pose Estimation","created":"2024-12-03","cited_by_count":9,"area":null},{"id":"2602.01661","title":"From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction","created":"2026-02-02","cited_by_count":9,"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":"2108.11801","title":"Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2307.11074","title":"Learning Dense UV Completion for Human Mesh Recovery","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2402.09650","title":"Foul prediction with estimated poses from soccer broadcast video","created":"2024-02-15","cited_by_count":7,"area":null},{"id":"2407.15451","title":"Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions","created":"2024-07-22","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","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":"2503.15671","title":"CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2208.04438","title":"Occlusion-Aware Instance Segmentation via BiLayer Network Architectures","created":"2022-08-08","cited_by_count":5,"area":null},{"id":"2208.11975","title":"Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2212.06242","title":"Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation","created":"2022-12-12","cited_by_count":5,"area":null},{"id":"2210.03686","title":"Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation","created":"2022-10-07","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":"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":"2503.18282","title":"TrackID3x3: A Dataset and Algorithm for Multi-Player Tracking with Identification and Pose Estimation in 3x3 Basketball Full-court Videos","created":"2025-03-24","cited_by_count":4,"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":"2202.00753","title":"ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2205.12646","title":"UniInst: Unique Representation for End-to-End Instance Segmentation","created":"2022-05-25","cited_by_count":2,"area":null},{"id":"2307.06737","title":"Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data","created":"2023-07-13","cited_by_count":2,"area":null},{"id":"2309.14072","title":"BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation","created":"2023-09-25","cited_by_count":2,"area":null},{"id":"2401.11738","title":"MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentation","created":"2024-01-22","cited_by_count":2,"area":null},{"id":"2403.12473","title":"PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery","created":"2024-03-19","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":"2405.01112","title":"Sports Analysis and VR Viewing System Based on Player Tracking and Pose Estimation with Multimodal and Multiview Sensors","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2412.01562","title":"Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2104.10414","title":"Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation","created":"2021-04-21","cited_by_count":1,"area":"distill"},{"id":"2108.07199","title":"Real-time Human-Centric Segmentation for Complex Video Scenes","created":"2021-08-16","cited_by_count":1,"area":null},{"id":"2210.02231","title":"Decanus to Legatus: Synthetic training for 2D-3D human pose lifting","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2212.00731","title":"FuRPE: Learning Full-body Reconstruction from Part Experts","created":"2022-11-30","cited_by_count":1,"area":null},{"id":"2302.08751","title":"MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Model","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2312.06409","title":"LiCamPose: Combining Multi-View LiDAR and RGB Cameras for Robust Single-timestamp 3D Human Pose Estimation","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2403.19336","title":"IVLMap: Instance-Aware Visual Language Grounding for Consumer Robot Navigation","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2404.11429","title":"CarcassFormer: An End-to-end Transformer-based Framework for Simultaneous Localization, Segmentation and Classification of Poultry Carcass Defect","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2408.11829","title":"FAKER: Full-body Anonymization with Human Keypoint Extraction for Real-time Video Deidentification","created":"2024-08-06","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":"2504.19032","title":"VISUALCENT: Visual Human Analysis using Dynamic Centroid Representation","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2505.17475","title":"PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.13027","title":"DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2601.08982","title":"SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowds","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2604.10485","title":"UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2606.07053","title":"TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation","created":"2026-06-05","cited_by_count":1,"area":"diffusion"},{"id":"2609.35718","title":"Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2107.08990","title":"A Benchmark for Gait Recognition under Occlusion Collected by Multi-Kinect SDAS","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2303.06800","title":"Object-Centric Multi-Task Learning for Human Instances","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2401.00155","title":"A comprehensive framework for occluded human pose estimation","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2401.00343","title":"SHARE: Single-view Human Adversarial REconstruction","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2403.01766","title":"Improving Visual Perception of a Social Robot for Controlled and In-the-wild Human-robot Interaction","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2404.12183","title":"Gait Recognition from Highly Compressed Videos","created":"2024-04-18","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":"2501.08815","title":"Human Pose-Constrained UV Map Estimation","created":"2025-01-15","cited_by_count":0,"area":null},{"id":"2501.12318","title":"BlanketGen2-Fit3D: Synthetic Blanket Augmentation Towards Improving Real-World In-Bed Blanket Occluded Human Pose Estimation","created":"2025-01-21","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":"2505.12130","title":"Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2509.07385","title":"Parse Graph-Based Visual-Language Interaction for Human Pose Estimation","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.20524","title":"InstructVTON: Optimal Auto-Masking and Natural-Language-Guided Interactive Style Control for Inpainting-Based Virtual Try-On","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.26681","title":"Improving Classification of Occluded Objects through Scene Context","created":"2025-10-30","cited_by_count":0,"area":null}],"next_cursor":"100"}