{"list":"other","total":66,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"1711.08229","title":"Integral Human Pose Regression","created":"2017-11-22","cited_by_count":256},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"1808.00157","title":"Instance-level Human Parsing via Part Grouping Network","created":"2018-08-01","cited_by_count":134},{"id":"1803.08225","title":"PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model","created":"2018-03-22","cited_by_count":133},{"id":"1701.01779","title":"Towards Accurate Multi-person Pose Estimation in the Wild","created":"2017-01-06","cited_by_count":131},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131},{"id":"1704.00159","title":"Compositional Human Pose Regression","created":"2017-04-01","cited_by_count":124},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112},{"id":"1803.10683","title":"Pose2Seg: Detection Free Human Instance Segmentation","created":"2018-03-28","cited_by_count":107},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103},{"id":"2402.14654","title":"Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot","created":"2024-02-22","cited_by_count":101},{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76},{"id":"1711.06475","title":"AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding","created":"2017-11-17","cited_by_count":73},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59},{"id":"1811.12596","title":"Parsing R-CNN for Instance-Level Human Analysis","created":"2018-11-30","cited_by_count":53},{"id":"1710.02322","title":"Human Pose Regression by Combining Indirect Part Detection and Contextual Information","created":"2017-10-06","cited_by_count":52},{"id":"2411.17646","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","created":"2024-11-26","cited_by_count":44},{"id":"2101.11223","title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","created":"2021-01-27","cited_by_count":30},{"id":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30},{"id":"2509.06607","title":"From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans","created":"2025-09-08","cited_by_count":27},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22},{"id":"2312.15895","title":"Semantic-aware SAM for Point-Prompted Instance Segmentation","created":"2023-12-26","cited_by_count":16},{"id":"2507.05427","title":"OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts","created":"2025-07-07","cited_by_count":15},{"id":"2306.07879","title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","created":"2023-06-13","cited_by_count":13},{"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},{"id":"2005.05708","title":"IterDet: Iterative Scheme for Object Detection in Crowded Environments","created":"2020-05-12","cited_by_count":12},{"id":"2508.15767","title":"ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling","created":"2025-08-21","cited_by_count":12},{"id":"2112.00627","title":"DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes","created":"2021-12-01","cited_by_count":11},{"id":"2511.03589","title":"Human Mesh Modeling for Anny Body","created":"2025-11-05","cited_by_count":10},{"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},{"id":"2412.02254","title":"ProbPose: A Probabilistic Approach to 2D Human Pose Estimation","created":"2024-12-03","cited_by_count":9},{"id":"2511.15586","title":"MHR: Momentum Human Rig","created":"2025-11-19","cited_by_count":9},{"id":"1704.01152","title":"Pose2Instance: Harnessing Keypoints for Person Instance Segmentation","created":"2017-04-04","cited_by_count":7},{"id":"2210.04014","title":"AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regression","created":"2022-10-08","cited_by_count":6},{"id":"2406.17382","title":"Automatic infant 2D pose estimation from videos: comparing seven deep neural network methods","created":"2024-06-25","cited_by_count":6},{"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},{"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},{"id":"2412.01562","title":"Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle","created":"2024-12-02","cited_by_count":2},{"id":"2512.15542","title":"BLANKET: Anonymizing Faces in Infant Video Recordings","created":"2025-12-17","cited_by_count":2},{"id":"2601.08982","title":"SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowds","created":"2026-01-13","cited_by_count":1}],"next_cursor":null}