{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:55:21Z","timestamp":1776441321932,"version":"3.51.2"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3184031","type":"journal-article","created":{"date-parts":[[2022,6,17]],"date-time":"2022-06-17T19:28:43Z","timestamp":1655494123000},"page":"65886-65900","source":"Crossref","is-referenced-by-count":15,"title":["Video Sparse Transformer With Attention-Guided Memory for Video Object Detection"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7702-499X","authenticated-orcid":false,"given":"Masato","family":"Fujitake","sequence":"first","affiliation":[{"name":"Department of Informatics, The Graduate University for Advanced Studies, SOKENDAI, Miura-gun, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9148-9822","authenticated-orcid":false,"given":"Akihiro","family":"Sugimoto","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_33"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2894261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00596"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3017411"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00712"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00678"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412056"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102907"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.330"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.101"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"ref20","first-page":"1","article-title":"Seq-NMS for video object detection","volume-title":"Proc. Workshops Int. Conf. Learn. Represent.","author":"Han"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00753"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412715"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00401"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413583"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413927"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_26"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16365"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref31","first-page":"1","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zaheer"},{"key":"ref32","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv:1904.10509"},{"key":"ref33","article-title":"Explicit sparse transformer: Concentrated attention through explicit selection","author":"Zhao","year":"2019","journal-title":"arXiv:1912.11637"},{"key":"ref34","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bertasius"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref36","first-page":"1","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref37","article-title":"TransVOD: End-to-end video object detection with spatial-temporal transformers","author":"Zhou","year":"2022","journal-title":"arXiv:2201.05047"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref40","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref41","volume-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref42","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_21"},{"key":"ref44","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00985"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475285"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16234"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00803"},{"key":"ref50","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639438"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2922479"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CRV50864.2020.00038"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.09.002"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_33"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09798833.pdf?arnumber=9798833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:14:54Z","timestamp":1706760894000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9798833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3184031","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}