{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:15:43Z","timestamp":1784211343148,"version":"3.55.0"},"reference-count":82,"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":"National Key Research and Development Program of China","award":["2019YFC1521104"],"award-info":[{"award-number":["2019YFC1521104"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72192821"],"award-info":[{"award-number":["72192821"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972157"],"award-info":[{"award-number":["61972157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["21511101200"],"award-info":[{"award-number":["21511101200"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Sailing Program","award":["22YF1420300"],"award-info":[{"award-number":["22YF1420300"]}]},{"DOI":"10.13039\/501100012325","name":"National Office for Philosophy and Social Sciences","doi-asserted-by":"publisher","award":["I8ZD22"],"award-info":[{"award-number":["I8ZD22"]}],"id":[{"id":"10.13039\/501100012325","id-type":"DOI","asserted-by":"publisher"}]}],"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.2022.3223955","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T19:57:43Z","timestamp":1669319863000},"page":"7853-7869","source":"Crossref","is-referenced-by-count":172,"title":["TransVOD: End-to-End Video Object Detection With Spatial-Temporal Transformers"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5331-050X","authenticated-orcid":false,"given":"Qianyu","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-8247","authenticated-orcid":false,"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"He","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0530-7231","authenticated-orcid":false,"given":"Yibo","family":"Yang","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1428-8848","authenticated-orcid":false,"given":"Guangliang","family":"Cheng","sequence":"additional","affiliation":[{"name":"SenseTime Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8735-2516","authenticated-orcid":false,"given":"Yunhai","family":"Tong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1653-4341","authenticated-orcid":false,"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413583"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413927"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00815"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6727"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref52","article-title":"Eatformer: Improving vision transformer inspired by evolutionary algorithm","author":"zhang","year":"2022"},{"key":"ref11","first-page":"431","article-title":"Mining inter-video proposal relations for video object detection","author":"han","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_31"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_2"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_42"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16365"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00401"},{"key":"ref51","first-page":"347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","article-title":"Trackformer: Multi-object tracking with transformers","author":"meinhardt","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref45","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref48","article-title":"Improving video instance segmentation via temporal pyramid routing","author":"li","year":"2021"},{"key":"ref47","article-title":"Adascale: Towards real-time video object detection using adaptive scaling","author":"chin","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref41","article-title":"High-performance semantic segmentation using very deep fully convolutional networks","author":"wu","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00351"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341600"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5220\/0007260002260233"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"ref5","article-title":"SEQ-NMS for video object detection","author":"han","year":"2016"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_14"},{"key":"ref81","article-title":"Objects as points","author":"zhou","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3094533"},{"key":"ref35","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00803"},{"key":"ref34","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16234"},{"key":"ref37","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"Transtrack: Multiple-object tracking with transformer","author":"sun","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00815"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3038913"},{"key":"ref30","first-page":"5686","article-title":"Mobile video object detection with temporally-aware feature maps","author":"liu","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref74","first-page":"485","article-title":"Video object detection with an aligned spatial-temporal memory","author":"xiao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref33","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3099409"},{"key":"ref32","article-title":"End-to-end video instance segmentation with transformers","author":"wang","year":"2020"},{"key":"ref76","article-title":"Object detection in video with spatial-temporal context aggregation","author":"luo","year":"2019"},{"key":"ref2","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475285"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.330"},{"key":"ref70","article-title":"MMTracking: OpenMMLab video perception toolbox and benchmark","year":"2020"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.03.110"},{"key":"ref72","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00678"},{"key":"ref68","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108323"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018529"},{"key":"ref25","first-page":"331","article-title":"Object detection in video with spatiotemporal sampling networks","author":"bertasius","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref69","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00753"},{"key":"ref66","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","first-page":"542","article-title":"Fully motion-aware network for video object detection","author":"wang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW50321.2020.9096948"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00985"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00712"},{"key":"ref29","article-title":"Looking fast and slow: Memory-guided mobile video object detection","author":"liu","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.255"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09960850.pdf?arnumber=9960850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:10:18Z","timestamp":1686593418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9960850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":82,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3223955","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]]}}}