{"url":"/task/multi-object-tracking","name":"Multi-Object Tracking","slug":"multi-object-tracking","description_markdown":"**Multi-Object Tracking** is a task in computer vision that involves detecting and tracking multiple objects within a video sequence. The goal is to identify and locate objects of interest in each frame and then associate them across frames to keep track of their movements over time. This task is challenging due to factors such as occlusion, motion blur, and changes in object appearance, and is typically solved using algorithms that integrate object detection and data association techniques.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":671,"papers_with_code":279,"benchmarks":22,"benchmark_tables_in_archive":22,"benchmark_tables_shown":22,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":43,"subtasks":6,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multi-object-tracking-on-mot17","slug":"multi-object-tracking-on-mot17","dataset":"MOT17","dataset_url":"/dataset/mot17","rows_in_archive":48,"metrics":["HOTA","MOTA","IDF1","AssA","DetA","e2e-MOT","Speed (FPS)"],"first_row_in_archive_order":{"model":"TrackTrack","paper_title":"Focusing on Tracks for Online Multi-Object Tracking","paper_url":"/paper/focusing-on-tracks-for-online-multi-object","paper_date":"2025-06-15","arxiv_id":null,"code_links":[{"title":"kamkyu94/TrackTrack","url":"https://github.com/kamkyu94/TrackTrack"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-dancetrack","slug":"multi-object-tracking-on-dancetrack","dataset":"DanceTrack","dataset_url":"/dataset/dancetrack","rows_in_archive":37,"metrics":["HOTA","MOTA","IDF1","AssA","DetA"],"first_row_in_archive_order":{"model":"SAM2MOT","paper_title":"SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation","paper_url":"/paper/sam2mot-a-novel-paradigm-of-multi-object","paper_date":"2025-04-06","arxiv_id":"2504.04519","code_links":[{"title":"TripleJoy/SAM2MOT","url":"https://github.com/TripleJoy/SAM2MOT"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-mot20-1","slug":"multi-object-tracking-on-mot20-1","dataset":"MOT20","dataset_url":"/dataset/mot20","rows_in_archive":27,"metrics":["HOTA","MOTA","IDF1","AssA","Speed (FPS)"],"first_row_in_archive_order":{"model":"BoostTrack++","paper_title":"BoostTrack++: using tracklet information to detect more objects in multiple object tracking","paper_url":"/paper/boosttrack-using-tracklet-information-to","paper_date":"2024-08-23","arxiv_id":"2408.13003","code_links":[{"title":"mikel-brostrom/boxmot","url":"https://github.com/mikel-brostrom/boxmot"},{"title":"vukasin-stanojevic/BoostTrack","url":"https://github.com/vukasin-stanojevic/BoostTrack"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-mot16","slug":"multi-object-tracking-on-mot16","dataset":"MOT16","dataset_url":"/dataset/mot16","rows_in_archive":24,"metrics":["MOTA","IDF1","IDs"],"first_row_in_archive_order":{"model":"PPTracking","paper_title":"PP-YOLOE: An evolved version of YOLO","paper_url":"/paper/pp-yoloe-an-evolved-version-of-yolo","paper_date":"2022-03-30","arxiv_id":"2203.16250","code_links":[{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"open-mmlab/mmyolo","url":"https://github.com/open-mmlab/mmyolo"},{"title":"PaddlePaddle/PaddleYOLO","url":"https://github.com/PaddlePaddle/PaddleYOLO"},{"title":"Nioolek/PPYOLOE_pytorch","url":"https://github.com/Nioolek/PPYOLOE_pytorch"},{"title":"Gaurav14cs17/YOLOE","url":"https://github.com/Gaurav14cs17/YOLOE"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/YOLOv5"},{"title":"Mind23-2/MindCode-130","url":"https://github.com/Mind23-2/MindCode-130"}],"syntology":{"n":27,"n_ran":5,"n_unverified":22,"n_pointer_only":0}}},{"leaderboard":"/sota/multi-object-tracking-on-sportsmot","slug":"multi-object-tracking-on-sportsmot","dataset":"SportsMOT","dataset_url":"/dataset/sportsmot","rows_in_archive":22,"metrics":["HOTA","IDF1","AssA","MOTA","DetA"],"first_row_in_archive_order":{"model":"DeepEIoU + GTA","paper_title":"GTA: Global Tracklet Association for Multi-Object Tracking in Sports","paper_url":"/paper/gta-global-tracklet-association-for-multi","paper_date":"2024-11-12","arxiv_id":"2411.08216","code_links":[{"title":"sjc042/gta-link","url":"https://github.com/sjc042/gta-link"},{"title":"zakroum-hicham/gta-DeepEIou-YOLO","url":"https://github.com/zakroum-hicham/gta-DeepEIou-YOLO"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-jrdb","slug":"multi-object-tracking-on-jrdb","dataset":"JRDB","dataset_url":"/dataset/jrdb","rows_in_archive":10,"metrics":["HOTA"],"first_row_in_archive_order":{"model":"OmniTrack","paper_title":"Omnidirectional Multi-Object Tracking","paper_url":"/paper/omnidirectional-multi-object-tracking","paper_date":"2025-03-06","arxiv_id":"2503.04565","code_links":[{"title":"xifen523/omnitrack","url":"https://github.com/xifen523/omnitrack"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-tao","slug":"multi-object-tracking-on-tao","dataset":"TAO","dataset_url":"/dataset/tao","rows_in_archive":9,"metrics":["TETA","LocA","AssocA","ClsA","Track mAP"],"first_row_in_archive_order":{"model":"AED (Co-DETR)","paper_title":"Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown","paper_url":"/paper/associate-everything-detected-facilitating","paper_date":"2024-09-14","arxiv_id":"2409.09293","code_links":[{"title":"balabooooo/aed","url":"https://github.com/balabooooo/aed"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-wildtrack","slug":"multi-object-tracking-on-wildtrack","dataset":"Wildtrack","dataset_url":"/dataset/wildtrack","rows_in_archive":9,"metrics":["IDF1","MOTA"],"first_row_in_archive_order":{"model":"MCBLT","paper_title":"MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos","paper_url":"/paper/bev-sushi-multi-target-multi-camera-3d","paper_date":"2024-12-01","arxiv_id":"2412.00692","code_links":[],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-2024-ai-city","slug":"multi-object-tracking-on-2024-ai-city","dataset":"2024 AI City Challenge","dataset_url":"/dataset/2024-ai-city-challenge-mtmc-people-tracking","rows_in_archive":8,"metrics":["HOTA","DetA","AssA","LocA"],"first_row_in_archive_order":{"model":"MCBLT","paper_title":"MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos","paper_url":"/paper/bev-sushi-multi-target-multi-camera-3d","paper_date":"2024-12-01","arxiv_id":"2412.00692","code_links":[],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-mots20","slug":"multi-object-tracking-on-mots20","dataset":"MOTS20","dataset_url":null,"rows_in_archive":6,"metrics":["sMOTSA","IDF1","IDs"],"first_row_in_archive_order":{"model":"ReMOTS","paper_title":"ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation","paper_url":"/paper/remots-self-supervised-refining-multi-object","paper_date":"2020-07-07","arxiv_id":"2007.03200","code_links":[],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-2d-mot-2015","slug":"multi-object-tracking-on-2d-mot-2015","dataset":"2D MOT 2015","dataset_url":"/dataset/mot15","rows_in_archive":4,"metrics":["MOTA","IDF1"],"first_row_in_archive_order":{"model":"GSDT","paper_title":"Joint Object Detection and Multi-Object Tracking with Graph Neural Networks","paper_url":"/paper/joint-detection-and-multi-object-tracking","paper_date":"2020-06-23","arxiv_id":"2006.13164","code_links":[{"title":"yongxinw/GSDT","url":"https://github.com/yongxinw/GSDT"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-hieve","slug":"multi-object-tracking-on-hieve","dataset":"HiEve","dataset_url":"/dataset/hieve","rows_in_archive":4,"metrics":["MOTA","IDF1"],"first_row_in_archive_order":{"model":"CSTrack","paper_title":"Rethinking the competition between detection and ReID in Multi-Object Tracking","paper_url":"/paper/rethinking-the-competition-between-detection","paper_date":"2020-10-23","arxiv_id":"2010.12138","code_links":[{"title":"Zhongdao/Towards-Realtime-MOT","url":"https://github.com/Zhongdao/Towards-Realtime-MOT"},{"title":"JudasDie/SOTS","url":"https://github.com/JudasDie/SOTS"},{"title":"ZhangwenguangHikvision/YoloV5_JDE_TensorRT_for_Track","url":"https://github.com/ZhangwenguangHikvision/YoloV5_JDE_TensorRT_for_Track"},{"title":"nemonameless/jde","url":"https://github.com/nemonameless/jde"}],"syntology":{"n":15,"n_ran":2,"n_unverified":13,"n_pointer_only":0}}},{"leaderboard":"/sota/multi-object-tracking-on-personpath22","slug":"multi-object-tracking-on-personpath22","dataset":"PersonPath22","dataset_url":"/dataset/personpath22","rows_in_archive":4,"metrics":["IDF1","MOTA"],"first_row_in_archive_order":{"model":"ByteTrack","paper_title":"Large Scale Real-World Multi-Person Tracking","paper_url":"/paper/large-scale-real-world-multi-person-tracking-1","paper_date":"2022-11-03","arxiv_id":"2211.02175","code_links":[{"title":"amazon-research/tracking-dataset","url":"https://github.com/amazon-research/tracking-dataset"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/multi-object-tracking-on-seadronessee","slug":"multi-object-tracking-on-seadronessee","dataset":"SeaDronesSee","dataset_url":"/dataset/seadronessee","rows_in_archive":3,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"Tracktor++","paper_title":"SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water","paper_url":"/paper/seadronessee-a-maritime-benchmark-for","paper_date":"2021-05-05","arxiv_id":"2105.01922","code_links":[],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-2dmot15-1","slug":"multi-object-tracking-on-2dmot15-1","dataset":"2DMOT15","dataset_url":"/dataset/mot15","rows_in_archive":2,"metrics":["MOTA","IDF1"],"first_row_in_archive_order":{"model":"FairMOT","paper_title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","paper_url":"/paper/a-simple-baseline-for-multi-object-tracking","paper_date":"2020-04-04","arxiv_id":"2004.01888","code_links":[{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"ifzhang/FairMOT","url":"https://github.com/ifzhang/FairMOT"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/fairmot"},{"title":"microsoft/FairMOT","url":"https://github.com/microsoft/FairMOT"},{"title":"microsoft/UDA","url":"https://github.com/microsoft/UDA"},{"title":"nolanzzz/MTMCT","url":"https://github.com/nolanzzz/MTMCT"},{"title":"chen-si-jia/Trajectory-Long-tail-Distribution-for-MOT","url":"https://github.com/chen-si-jia/Trajectory-Long-tail-Distribution-for-MOT"},{"title":"zengwbz/Face-Tracking-usingFairMOT","url":"https://github.com/zengwbz/Face-Tracking-usingFairMOT"},{"title":"dingwoai/FairMOT-BDD100K","url":"https://github.com/dingwoai/FairMOT-BDD100K"},{"title":"ydhcg-bobo/stcmot","url":"https://github.com/ydhcg-bobo/stcmot"},{"title":"harsh2912/people-tracking","url":"https://github.com/harsh2912/people-tracking"},{"title":"dhu-mmct/dhu-mmct","url":"https://github.com/dhu-mmct/dhu-mmct"},{"title":"cds-mipt/cds-tracking","url":"https://github.com/cds-mipt/cds-tracking"},{"title":"seominseok0429/vidoe_tracking-Reidentification-Action_recognition_Demo","url":"https://github.com/seominseok0429/vidoe_tracking-Reidentification-Action_recognition_Demo"},{"title":"ZJUT-ERCISS/zjut_mindvideo","url":"https://github.com/ZJUT-ERCISS/zjut_mindvideo/blob/master/msvideo/models/fairmot.py"},{"title":"ankitsinghsuraj/mot20","url":"https://github.com/ankitsinghsuraj/mot20"},{"title":"MindSpore-paper-code-3/code10","url":"https://github.com/MindSpore-paper-code-3/code10/tree/main/fairmot"},{"title":"nadinenijssen/Github_5AUA0_Project_G12T1","url":"https://github.com/nadinenijssen/Github_5AUA0_Project_G12T1"},{"title":"oljikeboost/PlayerTracking","url":"https://github.com/oljikeboost/PlayerTracking"},{"title":"MindSpore-paper-code-3/code3","url":"https://github.com/MindSpore-paper-code-3/code3/tree/main/fairmot"},{"title":"lilin19890401/FairMOT","url":"https://github.com/lilin19890401/FairMOT"},{"title":"MindSpore-paper-code-3/code8","url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/fairmot"},{"title":"nemonameless/fairmot","url":"https://github.com/nemonameless/fairmot"},{"title":"MindSpore-paper-code-3/code7","url":"https://github.com/MindSpore-paper-code-3/code7/tree/main/fairmot"},{"title":"15534081591/FairMOT","url":"https://github.com/15534081591/FairMOT"},{"title":"FlorentijnD/FairMOT","url":"https://github.com/FlorentijnD/FairMOT"},{"title":"Bangbangbanana/fairmot_mindspore","url":"https://github.com/Bangbangbanana/fairmot_mindspore"},{"title":"gsan2/FairMOT","url":"https://github.com/gsan2/FairMOT"},{"title":"HoganZhang/FairMOT","url":"https://github.com/HoganZhang/FairMOT"},{"title":"IMBINGO95/FairMOT","url":"https://github.com/IMBINGO95/FairMOT"},{"title":"jingcjie/FairMOT-mindspore-jupyter","url":"https://github.com/jingcjie/FairMOT-mindspore-jupyter"},{"title":"realdingke/mscai_softwareengineering_project","url":"https://github.com/realdingke/mscai_softwareengineering_project"},{"title":"Mind23-2/MindCode-42","url":"https://github.com/Mind23-2/MindCode-42"}],"syntology":{"n":53,"n_ran":8,"n_unverified":45,"n_pointer_only":0}}},{"leaderboard":"/sota/multi-object-tracking-on-mot15","slug":"multi-object-tracking-on-mot15","dataset":"MOT15","dataset_url":"/dataset/mot15","rows_in_archive":2,"metrics":["MOTA","MOTP"],"first_row_in_archive_order":{"model":"Baseline+MFW","paper_title":"Track to Detect and Segment: An Online Multi-Object Tracker","paper_url":"/paper/track-to-detect-and-segment-an-online-multi","paper_date":"2021-03-16","arxiv_id":"2103.08808","code_links":[{"title":"JialianW/TraDeS","url":"https://github.com/JialianW/TraDeS"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/multi-object-tracking-on-multiviewx","slug":"multi-object-tracking-on-multiviewx","dataset":"MultiviewX","dataset_url":"/dataset/multiviewx","rows_in_archive":2,"metrics":["IDF1","MOTA"],"first_row_in_archive_order":{"model":"TrackTacular (Bilinear Sampling)","paper_title":"Lifting Multi-View Detection and Tracking to the Bird's Eye View","paper_url":"/paper/lifting-multi-view-detection-and-tracking-to","paper_date":"2024-03-19","arxiv_id":"2403.12573","code_links":[{"title":"tteepe/tracktacular","url":"https://github.com/tteepe/tracktacular"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-uavdt","slug":"multi-object-tracking-on-uavdt","dataset":"UAVDT","dataset_url":"/dataset/uavdt","rows_in_archive":2,"metrics":["IDF1","MOTA"],"first_row_in_archive_order":{"model":"SAM2MOT","paper_title":"SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation","paper_url":"/paper/sam2mot-a-novel-paradigm-of-multi-object","paper_date":"2025-04-06","arxiv_id":"2504.04519","code_links":[{"title":"TripleJoy/SAM2MOT","url":"https://github.com/TripleJoy/SAM2MOT"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-bdd100k","slug":"multi-object-tracking-on-bdd100k","dataset":"BDD100K","dataset_url":"/dataset/bdd100k","rows_in_archive":1,"metrics":["TETA","AssocA","ClsA","LocA"],"first_row_in_archive_order":{"model":"CO-MOT","paper_title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","paper_url":"/paper/bridging-the-gap-between-end-to-end-and-non","paper_date":"2023-05-22","arxiv_id":"2305.12724","code_links":[{"title":"bingfengyan/visam","url":"https://github.com/bingfengyan/visam"},{"title":"BingfengYan/CO-MOT","url":"https://github.com/BingfengYan/CO-MOT"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-mot15-3d","slug":"multi-object-tracking-on-mot15-3d","dataset":"MOT15_3D","dataset_url":null,"rows_in_archive":1,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"MPLT","paper_title":"Using Panoramic Videos for Multi-person Localization and Tracking in a 3D Panoramic Coordinate","paper_url":"/paper/using-panoramic-videos-for-multi-person","paper_date":"2019-11-24","arxiv_id":"1911.10535","code_links":[{"title":"fandulu/MPLT","url":"https://github.com/fandulu/MPLT"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-synthehicle","slug":"multi-object-tracking-on-synthehicle","dataset":"Synthehicle","dataset_url":"/dataset/synthehicle","rows_in_archive":1,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"Baseline","paper_title":"Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Cities","paper_url":"/paper/synthehicle-multi-vehicle-multi-camera","paper_date":"2022-08-30","arxiv_id":"2208.14167","code_links":[{"title":"fubel/synthehicle","url":"https://github.com/fubel/synthehicle"}],"syntology":null}},{"leaderboard":"/sota/multi-object-tracking-on-visdrone2019","slug":"multi-object-tracking-on-visdrone2019","dataset":"VisDrone2019","dataset_url":null,"rows_in_archive":1,"metrics":["IDF1"],"first_row_in_archive_order":{"model":"DroneMOT","paper_title":"DroneMOT: Drone-based Multi-Object Tracking Considering Detection Difficulties and Simultaneous Moving of Drones and Objects","paper_url":"/paper/dronemot-drone-based-multi-object-tracking","paper_date":"2024-07-12","arxiv_id":"2407.09051","code_links":[{"title":"PenK1nG/DroneMOT","url":"https://github.com/PenK1nG/DroneMOT"}],"syntology":null}}],"datasets":[{"url":"/dataset/bdd100k","name":"BDD100K","full_name":"","num_papers_in_archive":469},{"url":"/dataset/mot17","name":"MOT17","full_name":"Multiple Object Tracking 17","num_papers_in_archive":291},{"url":"/dataset/motchallenge","name":"MOTChallenge","full_name":"","num_papers_in_archive":192},{"url":"/dataset/mot16","name":"MOT16","full_name":"Multiple Object Tracking 2016","num_papers_in_archive":149},{"url":"/dataset/virtual-kitti","name":"Virtual KITTI","full_name":"","num_papers_in_archive":133},{"url":"/dataset/uavdt","name":"UAVDT","full_name":"Unmanned Aerial Vehicle Benchmark Object Detection and Tracking","num_papers_in_archive":96},{"url":"/dataset/dancetrack","name":"DanceTrack","full_name":"","num_papers_in_archive":91},{"url":"/dataset/mot15","name":"MOT15","full_name":"Multiple Object Tracking 15","num_papers_in_archive":67},{"url":"/dataset/wildtrack","name":"Wildtrack","full_name":"","num_papers_in_archive":65},{"url":"/dataset/virtual-kitti-2","name":"Virtual KITTI 2","full_name":"","num_papers_in_archive":53},{"url":"/dataset/tao","name":"TAO","full_name":"Tracking Any Object Dataset","num_papers_in_archive":49},{"url":"/dataset/mot20","name":"MOT20","full_name":"MOT20","num_papers_in_archive":34},{"url":"/dataset/jrdb","name":"JRDB","full_name":"JackRabbot Dataset and Benchmark","num_papers_in_archive":33},{"url":"/dataset/sportsmot","name":"SportsMOT","full_name":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","num_papers_in_archive":32},{"url":"/dataset/kitti-mots","name":"KITTI MOTS","full_name":"KITTI Multi-Object Tracking and Segmentation (MOTS) Evaluation","num_papers_in_archive":28},{"url":"/dataset/multiviewx","name":"MultiviewX","full_name":null,"num_papers_in_archive":26},{"url":"/dataset/hieve","name":"HiEve","full_name":"Human-in-Events","num_papers_in_archive":19},{"url":"/dataset/seadronessee","name":"SeaDronesSee","full_name":"SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water","num_papers_in_archive":18},{"url":"/dataset/gmot-40","name":"GMOT-40","full_name":"Generic Multiple Object Tracking (GMOT)","num_papers_in_archive":12},{"url":"/dataset/2024-ai-city-challenge-mtmc-people-tracking","name":"2024 AI City Challenge","full_name":"","num_papers_in_archive":10},{"url":"/dataset/pathtrack","name":"PathTrack","full_name":"","num_papers_in_archive":9},{"url":"/dataset/dttd2","name":"DTTD-Mobile","full_name":"","num_papers_in_archive":8},{"url":"/dataset/mmptrack","name":"MMPTRACK","full_name":"Multi-camera Multiple People Tracking Dataset","num_papers_in_archive":6},{"url":"/dataset/youtube-vis-2022-validation","name":"Youtube-VIS 2022 Validation","full_name":"","num_papers_in_archive":6},{"url":"/dataset/3d-pop","name":"3D-POP","full_name":"","num_papers_in_archive":3},{"url":"/dataset/divotrack","name":"DIVOTrack","full_name":"","num_papers_in_archive":3},{"url":"/dataset/groot","name":"GroOT","full_name":"Grounded Multiple Object Tracking","num_papers_in_archive":3},{"url":"/dataset/raileye3d-dataset","name":"RailEye3D Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/soccernet-gsr","name":"SoccerNet-GSR","full_name":"SoccerNet Game State Reconstruction","num_papers_in_archive":3},{"url":"/dataset/synthehicle","name":"Synthehicle","full_name":"","num_papers_in_archive":3},{"url":"/dataset/bee23","name":"BEE23","full_name":"Multi-bee Tracking Benchmark","num_papers_in_archive":2},{"url":"/dataset/cholectrack20","name":"CholecTrack20","full_name":"Multi-Perspective Multi-Class Multi-Object Tracking Dataset For Surgical Tools","num_papers_in_archive":2},{"url":"/dataset/personpath22","name":"PersonPath22","full_name":"","num_papers_in_archive":2},{"url":"/dataset/3d-zef","name":"3D-ZeF","full_name":"3D ZebraFish Tracking Benchmark","num_papers_in_archive":1},{"url":"/dataset/aerialmpt","name":"AerialMPT","full_name":"","num_papers_in_archive":1},{"url":"/dataset/bucktales","name":"BuckTales","full_name":"A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes","num_papers_in_archive":1},{"url":"/dataset/fishtrac","name":"FISHTRAC","full_name":"Nguyen Minh Khiem","num_papers_in_archive":1},{"url":"/dataset/ha-vid","name":"HA-ViD","full_name":"HA-ViD: A Human Assembly Video Dataset","num_papers_in_archive":1},{"url":"/dataset/ltft","name":"LTFT","full_name":"Long-Term Face Tracking","num_papers_in_archive":1},{"url":"/dataset/soccertrack-dataset","name":"SoccerTrack Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tao-amodal","name":"TAO-Amodal","full_name":"","num_papers_in_archive":1},{"url":"/dataset/timbervision-dataset","name":"TimberVision","full_name":"TimberVision","num_papers_in_archive":1},{"url":"/dataset/vetra","name":"VETRA","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/3d-multi-object-tracking","name":"3D Multi-Object Tracking"},{"url":"/task/grounded-multiple-object-tracking","name":"Grounded Multiple Object Tracking"},{"url":"/task/multi-animal-tracking-with-identification","name":"Multi-Animal Tracking with identification"},{"url":"/task/real-time-multi-object-tracking","name":"Real-Time Multi-Object Tracking"},{"url":"/task/referring-multi-object-tracking","name":"Referring Multi-Object Tracking"},{"url":"/task/trajectory-long-tail-distribution-for-muti","name":"Trajectory Long-tail Distribution for Muti-object Tracking"}],"parent_tasks":[{"url":"/task/object-tracking","name":"Object Tracking"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":279,"tagged_in_all":671,"items":[{"url":"/paper/simple-online-and-realtime-tracking","title":"Simple Online and Realtime Tracking","date":"2016-02-02","arxiv_id":"1602.00763","repositories_listed":56,"syntology":{"n":40,"n_ran":15,"n_unverified":25,"n_pointer_only":7}},{"url":"/paper/a-simple-baseline-for-multi-object-tracking","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","date":"2020-04-04","arxiv_id":"2004.01888","repositories_listed":33,"syntology":{"n":53,"n_ran":8,"n_unverified":45,"n_pointer_only":0}},{"url":"/paper/strongsort-make-deepsort-great-again","title":"StrongSORT: Make DeepSORT Great Again","date":"2022-02-28","arxiv_id":"2202.13514","repositories_listed":14,"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":2}},{"url":"/paper/tracking-without-bells-and-whistles","title":"Tracking without bells and whistles","date":"2019-03-13","arxiv_id":"1903.05625","repositories_listed":13,"syntology":{"n":14,"n_ran":3,"n_unverified":11,"n_pointer_only":2}},{"url":"/paper/towards-real-time-multi-object-tracking","title":"Towards Real-Time Multi-Object Tracking","date":"2019-09-27","arxiv_id":"1909.12605","repositories_listed":12,"syntology":{"n":36,"n_ran":2,"n_unverified":34,"n_pointer_only":0}},{"url":"/paper/bytetrack-multi-object-tracking-by-1","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","date":"2021-10-13","arxiv_id":"2110.06864","repositories_listed":10,"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/pp-yoloe-an-evolved-version-of-yolo","title":"PP-YOLOE: An evolved version of YOLO","date":"2022-03-30","arxiv_id":"2203.16250","repositories_listed":8,"syntology":{"n":27,"n_ran":5,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/mot16-a-benchmark-for-multi-object-tracking","title":"MOT16: A Benchmark for Multi-Object Tracking","date":"2016-03-02","arxiv_id":"1603.00831","repositories_listed":8,"syntology":{"n":38,"n_ran":11,"n_unverified":27,"n_pointer_only":1}},{"url":"/paper/bot-sort-robust-associations-multi-pedestrian","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","date":"2022-06-29","arxiv_id":"2206.14651","repositories_listed":7,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/observation-centric-sort-rethinking-sort-for","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","date":"2022-03-27","arxiv_id":"2203.14360","repositories_listed":7,"syntology":{"n":31,"n_ran":15,"n_unverified":16,"n_pointer_only":2}},{"url":"/paper/tracking-objects-as-points","title":"Tracking Objects as Points","date":"2020-04-02","arxiv_id":"2004.01177","repositories_listed":7,"syntology":{"n":16,"n_ran":4,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/simpletrack-rethinking-and-improving-the-jde","title":"SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking","date":"2022-03-08","arxiv_id":"2203.03985","repositories_listed":6,"syntology":null},{"url":"/paper/trasw-tracklet-switch-adversarial-attacks","title":"Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers","date":"2021-11-17","arxiv_id":"2111.08954","repositories_listed":5,"syntology":null},{"url":"/paper/hota-a-higher-order-metric-for-evaluating","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","date":"2020-09-16","arxiv_id":"2009.07736","repositories_listed":5,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/motrv2-bootstrapping-end-to-end-multi-object","title":"MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors","date":"2022-11-17","arxiv_id":"2211.09791","repositories_listed":4,"syntology":null},{"url":"/paper/improving-object-detection-multi-object","title":"Improving Object Detection, Multi-object Tracking, and Re-Identification for Disaster Response Drones","date":"2022-01-05","arxiv_id":"2201.01494","repositories_listed":4,"syntology":null},{"url":"/paper/tracking-pedestrian-heads-in-dense-crowd","title":"Tracking Pedestrian Heads in Dense Crowd","date":"2021-03-24","arxiv_id":"2103.13516","repositories_listed":4,"syntology":null},{"url":"/paper/model-free-vehicle-tracking-and-state","title":"Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences","date":"2021-03-10","arxiv_id":"2103.06028","repositories_listed":4,"syntology":null},{"url":"/paper/hardnet-mseg-a-simple-encoder-decoder-polyp","title":"HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS","date":"2021-01-18","arxiv_id":"2101.07172","repositories_listed":4,"syntology":null},{"url":"/paper/rethinking-the-competition-between-detection","title":"Rethinking the competition between detection and ReID in Multi-Object Tracking","date":"2020-10-23","arxiv_id":"2010.12138","repositories_listed":4,"syntology":{"n":15,"n_ran":2,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/extended-isolation-forest","title":"Extended Isolation Forest","date":"2018-11-06","arxiv_id":"1811.02141","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/bdd100k-a-diverse-driving-video-database-with","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","date":"2018-05-12","arxiv_id":"1805.04687","repositories_listed":4,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/track-initialization-and-re-identification","title":"Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking","date":"2024-05-28","arxiv_id":"2405.18606","repositories_listed":3,"syntology":null},{"url":"/paper/deep-oc-sort-multi-pedestrian-tracking-by","title":"Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification","date":"2023-02-23","arxiv_id":"2302.11813","repositories_listed":3,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/the-1st-place-solution-for-eccv-2022-multiple","title":"The 1st-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge","date":"2022-10-27","arxiv_id":"2210.15281","repositories_listed":3,"syntology":null},{"url":"/paper/dancetrack-multi-object-tracking-in-uniform","title":"DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion","date":"2021-11-29","arxiv_id":"2111.14690","repositories_listed":3,"syntology":null},{"url":"/paper/exploring-simple-3d-multi-object-tracking-for","title":"Exploring Simple 3D Multi-Object Tracking for Autonomous Driving","date":"2021-08-23","arxiv_id":"2108.10312","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/real-time-pear-fruit-detection-and-counting","title":"Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT","date":"2021-07-14","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/eagermot-3d-multi-object-tracking-via-sensor","title":"EagerMOT: 3D Multi-Object Tracking via Sensor Fusion","date":"2021-04-29","arxiv_id":"2104.14682","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/quasi-dense-instance-similarity-learning","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","date":"2020-06-11","arxiv_id":"2006.06664","repositories_listed":3,"syntology":null}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}