{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:41:58Z","timestamp":1784227318075,"version":"3.55.0"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ANR ML3RI Project","award":["ANR-19-CE33-0008-01"],"award-info":[{"award-number":["ANR-19-CE33-0008-01"]}]},{"name":"H2020 SPRING Project","award":["GA 871245"],"award-info":[{"award-number":["GA 871245"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3225078","type":"journal-article","created":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T19:51:18Z","timestamp":1669665078000},"page":"7820-7835","source":"Crossref","is-referenced-by-count":183,"title":["TransCenter: Transformers With Dense Representations for Multiple-Object Tracking"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1043-0656","authenticated-orcid":false,"given":"Yihong","family":"Xu","sequence":"first","affiliation":[{"name":"Inria and now with Valeo.ai, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5396-9251","authenticated-orcid":false,"given":"Yutong","family":"Ban","sequence":"additional","affiliation":[{"name":"Distributed Robotics Lab, CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Delorme","sequence":"additional","affiliation":[{"name":"Inria Grenoble Rhône-Alpes, Montbonnot-Saint-Martin, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4031-5886","authenticated-orcid":false,"given":"Chuang","family":"Gan","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5473-3566","authenticated-orcid":false,"given":"Daniela","family":"Rus","sequence":"additional","affiliation":[{"name":"Distributed Robotics Lab, CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5354-1084","authenticated-orcid":false,"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[{"name":"Inria Grenoble Rhône-Alpes, Montbonnot-Saint-Martin, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.41"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"ref56","first-page":"17","article-title":"Performance measures and a data set for multi-target, multi-camera tracking","author":"ristani","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"ref59","first-page":"290","article-title":"PathTrack: Fast trajectory annotation with path supervision","author":"santiago","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587581"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01410"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref52","article-title":"TrackMPNN: A message passing graph neural architecture for multi-object tracking","author":"rangesh","year":"2021"},{"key":"ref96","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020"},{"key":"ref11","article-title":"MOT20: A benchmark for multi object tracking in crowded scenes","author":"dendorfer","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.349"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref54","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref18","article-title":"YOLOX: Exceeding yolo series in 2021","author":"ge","year":"2021"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00248"},{"key":"ref51","first-page":"304","article-title":"Pedestrian detection: A benchmark","author":"piotr","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref95","article-title":"Looking beyond two frames: End-to-end multi-object tracking using spatial and temporal transformers","author":"zhu","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_9"},{"key":"ref94","article-title":"Objects as points","author":"zhou","year":"2019"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.357"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref46","article-title":"MOT16: A benchmark for multi-object tracking","author":"milan","year":"2016"},{"key":"ref45","article-title":"TrackFormer: Multi-object tracking with transformers","author":"meinhardt","year":"2021"},{"key":"ref89","article-title":"Bag of freebies for training object detection neural networks","author":"zhang","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11194"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/74"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2996609"},{"key":"ref41","article-title":"Unsupervised multiple-object tracking with a dynamical variational autoencoder","author":"lin","year":"2022"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.474"},{"key":"ref44","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref88","article-title":"FairMOT: On the fairness of detection and re-identification in multiple object tracking","author":"zhang","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.12.037"},{"key":"ref87","article-title":"ByteTrack: Multi-object tracking by associating every detection box","author":"zhang","year":"2021"},{"key":"ref49","article-title":"GCNNMatch: Graph convolutional neural networks for multi-object tracking via sinkhorn normalization","author":"papakis","year":"2020"},{"key":"ref8","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00628"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486597"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00680"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref40","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref84","article-title":"End-to-end multiple-object tracking with transformer","author":"zeng","year":"2021"},{"key":"ref83","article-title":"RelationTrack: Relation-aware multiple object tracking with decoupled representation","author":"yu","year":"2021"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00682"},{"key":"ref35","first-page":"734","article-title":"CornerNet: Detecting objects as paired keypoints","author":"law","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref79","article-title":"End-to-end deep learning for person search","author":"xiao","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.534"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206735"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.27"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932301"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00653"},{"key":"ref30","article-title":"Simple unsupervised multi-object tracking","author":"karthik","year":"2020"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341164"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00943"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"ref32","article-title":"A multi-cut formulation for joint segmentation and tracking of multiple objects","author":"keuper","year":"2016"},{"key":"ref76","article-title":"Joint 3D tracking and forecasting with graph neural network and diversity sampling","author":"weng","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2953020"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION43075.2019.9011441"},{"key":"ref39","article-title":"Detr for crowd pedestrian detection","author":"lin","year":"2020"},{"key":"ref38","article-title":"Rethinking the competition between detection and reid in multi-object tracking","author":"liang","year":"2020"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00387"},{"key":"ref70","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561110"},{"key":"ref72","first-page":"1","article-title":"PVT V2: Improved baselines with pyramid vision transformer","author":"wang","year":"2022","journal-title":"Proc Computational Visual Media (CVM)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","article-title":"Open synthetic dataset for improving cyclist detection","author":"thomas","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00526"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.394"},{"key":"ref26","first-page":"4364","article-title":"Lifted disjoint paths with application in multiple object tracking","author":"hornakova","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50516-5_5"},{"key":"ref64","article-title":"TransTrack: Multiple-object tracking with transformer","author":"sun","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01219"},{"key":"ref22","article-title":"Mat: Motion-aware multi-object tracking","author":"han","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00804"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299138"},{"key":"ref28","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"jia","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00936"},{"key":"ref29","article-title":"TransGAN: Two transformers can make one strong GAN","author":"jiang","year":"2021"},{"key":"ref60","article-title":"Tracklets predicting based adaptive graph tracking","author":"shan","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2750082"},{"key":"ref61","article-title":"CrowdHuman: A benchmark for detecting human in a crowd","author":"shao","year":"2018"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09964258.pdf?arnumber=9964258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:37:59Z","timestamp":1685381879000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9964258\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":96,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3225078","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}