{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T15:40:50Z","timestamp":1778514050330,"version":"3.51.4"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["U21A20514"],"award-info":[{"award-number":["U21A20514"]}],"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":["62071404"],"award-info":[{"award-number":["62071404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"FuXiaQuan National Independent Innovation Demonstration Zone Collaborative Innovation Platform","award":["3502ZCQXT2022008"],"award-info":[{"award-number":["3502ZCQXT2022008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3292615","type":"journal-article","created":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T17:16:51Z","timestamp":1688577411000},"page":"2109-2123","source":"Crossref","is-referenced-by-count":10,"title":["Class-Aware Dual-Supervised Aggregation Network for Video Object Detection"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9127-3404","authenticated-orcid":false,"given":"Qiang","family":"Qi","sequence":"first","affiliation":[{"name":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7160","authenticated-orcid":false,"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6913-9786","authenticated-orcid":false,"given":"Hanzi","family":"Wang","sequence":"additional","affiliation":[{"name":"Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2450020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2498760"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2748459"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751966"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2915191"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3177942"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3034487"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2508603"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_24"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108587"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3164253"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16365"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3094533"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref18","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"ref22","article-title":"Yolov4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16179"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref27","article-title":"Seq-NMS for video object detection","author":"Han","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2910529"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475285"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"ref32","first-page":"586","article-title":"VSE++ : Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref34","first-page":"2351","article-title":"Ensemble distillation for robust model fusion in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475253"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00985"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969787"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3088880"},{"key":"ref39","first-page":"565","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19965"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01507-2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_26"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3183646"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3238818"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00678"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413927"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413583"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3176721"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00712"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_33"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00753"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_21"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00815"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018529"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00401"},{"key":"ref62","article-title":"Object detection in video with spatial-temporal context aggregation","author":"Luo","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00803"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_2"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990070"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6727"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3099409"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_30"},{"issue":"11","key":"ref69","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10173615.pdf?arnumber=10173615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T20:21:45Z","timestamp":1707250905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10173615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3292615","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}