{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T18:16:48Z","timestamp":1784917008941,"version":"3.55.0"},"reference-count":101,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ARC","award":["CE140100016"],"award-info":[{"award-number":["CE140100016"]}]},{"name":"ARC","award":["FL130100102"],"award-info":[{"award-number":["FL130100102"]}]},{"name":"ARC","award":["DP200102427"],"award-info":[{"award-number":["DP200102427"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,11,1]]},"DOI":"10.1109\/tpami.2022.3213073","type":"journal-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:18:18Z","timestamp":1665433098000},"page":"12783-12797","source":"Crossref","is-referenced-by-count":61,"title":["Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6735-0553","authenticated-orcid":false,"given":"Tianyu","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Systems Engineering, Monash University, Clayton, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8133-0102","authenticated-orcid":false,"given":"Markus","family":"Hiller","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahsa","family":"Ehsanpour","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongkai","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Systems Engineering, Monash University, Clayton, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Drummond","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7790-6423","authenticated-orcid":false,"given":"Ian","family":"Reid","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8659-8773","authenticated-orcid":false,"given":"Hamid","family":"Rezatofighi","sequence":"additional","affiliation":[{"name":"Department of Data Science and AI, Monash University, Clayton, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995311"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247893"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref4","volume-title":"Design and Analysis of Modern Tracking Systems","author":"Blackman","year":"1999"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.1983.1145560"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.349"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION43075.2019.9011349"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1117\/12.179066"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.87"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.234"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00549"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.59"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.41"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01297"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01081"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.330"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929520"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.4153\/CJM-1956-045-5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref31","article-title":"Deep perm-set net: Learn to predict sets with unknown permutation and cardinality using deep neural networks","author":"Rezatofighi","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3122970"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref34","article-title":"TransTrack: Multiple-object tracking with transformer","author":"Sun","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.533"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995384"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00632"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247907"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_40"},{"key":"ref41","article-title":"Improvements in pedestrian tracking by a generalized potential field approach","author":"Particke","year":"2017","journal-title":"Mobil. TUM, Intell. Transport Syst. Theory Pract."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SDF.2017.8126388"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/PLANS.2018.8373383"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00057"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451739"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2993073"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05710-7_34"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01410"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00169"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00628"},{"key":"ref51","first-page":"4364","article-title":"Lifted disjoint paths with application in multiple object tracking","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hornakova"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00627"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2882192"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.394"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00247"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561110"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533455"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00248"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00387"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref65","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref66","article-title":"Stand-alone self-attention in vision models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ramachandran"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref70","article-title":"MOT16: A benchmark for multi-object tracking","author":"Milan","year":"2016"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2849374"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2940922"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_7"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_23"},{"key":"ref75","first-page":"1","article-title":"Real-time multiple people tracking with deeply learned candidate selection and person re-identification","volume-title":"Proc. IEEE Int. Conf. Multimedia Expo","author":"Long"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00409"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00680"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00682"},{"key":"ref79","article-title":"MOT20: A benchmark for multi object tracking in crowded scenes","author":"Dendorfer","year":"2020"},{"key":"ref80","article-title":"MOTChallenge 2015: Towards a benchmark for multi-target tracking","author":"Leal-Taix\u00e9","year":"2015"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01375-2"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref85","article-title":"CrowdHuman: A benchmark for detecting human in a crowd","author":"Shao","year":"2018"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587581"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.360"},{"key":"ref88","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021"},{"key":"ref89","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876253"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00105"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078517"},{"key":"ref93","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00627"},{"key":"ref96","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00634"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_9"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.008"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS52988.2021.9663836"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10269680\/09914676.pdf?arnumber=9914676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:55:05Z","timestamp":1719345305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9914676\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":101,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3213073","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":[[2023,11,1]]}}}