{"list":"other","total":72,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218},{"id":"2011.08036","title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","created":"2020-11-16","cited_by_count":211},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200},{"id":"2007.09545","title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose","created":"2020-07-19","cited_by_count":183},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"1908.05806","title":"Cross-Domain Adaptation for Animal Pose Estimation","created":"2019-08-16","cited_by_count":108},{"id":"1908.09220","title":"Single-Stage Multi-Person Pose Machines","created":"2019-08-24","cited_by_count":95},{"id":"2104.03176","title":"On Self-Contact and Human Pose","created":"2021-04-07","cited_by_count":89},{"id":"2004.00945","title":"PaStaNet: Toward Human Activity Knowledge Engine","created":"2020-04-02","cited_by_count":80},{"id":"2203.16250","title":"PP-YOLOE: An evolved version of YOLO","created":"2022-03-30","cited_by_count":75},{"id":"1906.07538","title":"Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection","created":"2019-06-18","cited_by_count":73},{"id":"1612.04402","title":"Finding Tiny Faces","created":"2016-12-13","cited_by_count":72},{"id":"2204.06806","title":"YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss","created":"2022-04-14","cited_by_count":68},{"id":"1904.03629","title":"Adaptive NMS: Refining Pedestrian Detection in a Crowd","created":"2019-04-07","cited_by_count":66},{"id":"2211.03679","title":"Body Part-Based Representation Learning for Occluded Person Re-Identification","created":"2022-11-07","cited_by_count":64},{"id":"1711.07752","title":"Repulsion Loss: Detecting Pedestrians in a Crowd","created":"2017-11-21","cited_by_count":62},{"id":"2003.09163","title":"Detection in Crowded Scenes: One Proposal, Multiple Predictions","created":"2020-03-20","cited_by_count":59},{"id":"2204.06184","title":"COAP: Compositional Articulated Occupancy of People","created":"2022-04-13","cited_by_count":59},{"id":"1807.08407","title":"Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd","created":"2018-07-23","cited_by_count":58},{"id":"2103.02440","title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","created":"2021-03-03","cited_by_count":55},{"id":"1710.06555","title":"Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification","created":"2017-10-18","cited_by_count":52},{"id":"1912.13344","title":"Learning 3D Human Shape and Pose from Dense Body Parts","created":"2019-12-31","cited_by_count":48},{"id":"2302.01593","title":"Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation","created":"2023-02-03","cited_by_count":48},{"id":"2103.13516","title":"Tracking Pedestrian Heads in Dense Crowd","created":"2021-03-24","cited_by_count":42},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41},{"id":"2010.09676","title":"Detecting Hands and Recognizing Physical Contact in the Wild","created":"2020-10-19","cited_by_count":38},{"id":"2205.01666","title":"DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks","created":"2022-05-03","cited_by_count":38},{"id":"2003.12729","title":"NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing","created":"2020-03-28","cited_by_count":36},{"id":"2105.14185","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","created":"2021-05-29","cited_by_count":34},{"id":"2207.14192","title":"Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection","created":"2022-07-28","cited_by_count":34},{"id":"2203.07669","title":"Progressive End-to-End Object Detection in Crowded Scenes","created":"2022-03-15","cited_by_count":31},{"id":"1909.06826","title":"PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes","created":"2019-09-15","cited_by_count":30},{"id":"2202.06851","title":"HAKE: A Knowledge Engine Foundation for Human Activity Understanding","created":"2022-02-14","cited_by_count":28},{"id":"2111.14173","title":"CDGNet: Class Distribution Guided Network for Human Parsing","created":"2021-11-28","cited_by_count":26},{"id":"2003.08069","title":"Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification","created":"2020-03-18","cited_by_count":23},{"id":"2210.13861","title":"SUPR: A Sparse Unified Part-Based Human Representation","created":"2022-10-25","cited_by_count":21},{"id":"1803.09256","title":"Detecting Heads using Feature Refine Net and Cascaded Multi-Scale Architecture","created":"2018-03-25","cited_by_count":18},{"id":"1909.10674","title":"Relational Learning for Joint Head and Human Detection","created":"2019-09-24","cited_by_count":14},{"id":"2207.06854","title":"AIParsing: Anchor-free Instance-level Human Parsing","created":"2022-07-14","cited_by_count":14},{"id":"2103.05997","title":"Quality-Aware Network for Human Parsing","created":"2021-03-10","cited_by_count":13},{"id":"1909.09998","title":"Double Anchor R-CNN for Human Detection in a Crowd","created":"2019-09-22","cited_by_count":10},{"id":"2104.12389","title":"Variational Pedestrian Detection","created":"2021-04-26","cited_by_count":10},{"id":"1511.07917","title":"Context-aware CNNs for person head detection","created":"2015-11-24","cited_by_count":9},{"id":"2110.00988","title":"Keypoint Communities","created":"2021-10-03","cited_by_count":8},{"id":"2210.12758","title":"Beta R-CNN: Looking into Pedestrian Detection from Another Perspective","created":"2022-10-23","cited_by_count":8},{"id":"1902.07017","title":"Detector-in-Detector: Multi-Level Analysis for Human-Parts","created":"2019-02-19","cited_by_count":6},{"id":"2112.13635","title":"AdaptivePose: Human Parts as Adaptive Points","created":"2021-12-27","cited_by_count":6},{"id":"2212.07652","title":"Body-Part Joint Detection and Association via Extended Object Representation","created":"2022-12-15","cited_by_count":5},{"id":"2111.13888","title":"Head and Body: Unified Detector and Graph Network for Person Search in Media","created":"2021-11-27","cited_by_count":1}],"next_cursor":null}