{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T08:47:44Z","timestamp":1768812464940,"version":"3.49.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836011"],"award-info":[{"award-number":["61836011"]}],"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":["61822208"],"award-info":[{"award-number":["61822208"]}],"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":["61632019"],"award-info":[{"award-number":["61632019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Yuth Innovation Promotion Association CAS","award":["2018497"],"award-info":[{"award-number":["2018497"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.2990070","type":"journal-article","created":{"date-parts":[[2020,4,23]],"date-time":"2020-04-23T19:58:36Z","timestamp":1587671916000},"page":"846-858","source":"Crossref","is-referenced-by-count":51,"title":["Single Shot Video Object Detector"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9624-7451","authenticated-orcid":false,"given":"Jiajun","family":"Deng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4344-8898","authenticated-orcid":false,"given":"Yingwei","family":"Pan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7587-101X","authenticated-orcid":false,"given":"Ting","family":"Yao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7732","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Foveabox: Beyond anchor-based object detector","author":"kong","year":"2019","journal-title":"arXiv preprint arXiv 1904 01870"},{"key":"ref38","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2013","journal-title":"arXiv preprint arXiv 1312 6229"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2829602"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2759508"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2916104"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00057"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01172"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01388"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00234"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref62","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Int Conf on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018529"},{"key":"ref27","article-title":"Light-head r-cnn: In defense of two-stage object detector","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1711 07128"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00401"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref68","article-title":"Ilsvrc2016 object detection from video: Team nuist","author":"yang","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","first-page":"5686","article-title":"Mobile video object detection with temporally-aware feature maps","author":"liu","year":"0","journal-title":"Proc IEEE Con Comput Vision and Pattern Recognit"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_30"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_33"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00753"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"ref51","first-page":"3832","article-title":"Learning deep intrinsic video representation by exploring temporal coherence and graph structure","author":"pan","year":"0","journal-title":"IJCAI"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350937"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.304"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref55","article-title":"Weakly-supervised action localization by generative attention modeling","author":"shi","year":"0","journal-title":"Proc IEEE Con Comput Vision and Pattern Recognit"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01233"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref12","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"liu","year":"0","journal-title":"European Conf on Computer Vision"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.330"},{"key":"ref16","article-title":"Seq-nms for video object detection","author":"han","year":"2016","journal-title":"arXiv preprint arXiv 1602 00377"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.101"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_21"},{"key":"ref4","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref8","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"0","journal-title":"Adv in Neural Info Proc Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01418"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00712"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.95"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"ref44","article-title":"Object detection in videos by high quality object linking","author":"tang","year":"2018","journal-title":"arXiv preprint arXiv 1801 09030"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018803"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09076794.pdf?arnumber=9076794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:27Z","timestamp":1652194287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9076794\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.2990070","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}