{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T00:18:59Z","timestamp":1793146739389,"version":"4.5.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CMMI-1646162"],"award-info":[{"award-number":["CMMI-1646162"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CMMI-1954548"],"award-info":[{"award-number":["CMMI-1954548"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tcsvt.2021.3094533","type":"journal-article","created":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T20:05:45Z","timestamp":1625515545000},"page":"8165-8178","source":"Crossref","is-referenced-by-count":33,"title":["Class-Aware Feature Aggregation Network for Video Object Detection"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6148-1114","authenticated-orcid":false,"given":"Liang","family":"Han","sequence":"first","affiliation":[{"name":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1430-0237","authenticated-orcid":false,"given":"Pichao","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9602-6488","authenticated-orcid":false,"given":"Zhaozheng","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and the Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7320-1119","authenticated-orcid":false,"given":"Fan","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9305-8524","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00678"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_30"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_10"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref31","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref30","article-title":"Looking fast and slow: Memory-guided mobile video object detection","author":"liu","year":"2019","journal-title":"arXiv 1903 10172"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.95"},{"key":"ref35","article-title":"Seq-NMS for video object detection","author":"han","year":"2016","journal-title":"arXiv 1602 08465"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_14"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00815"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00753"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00596"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413927"},{"key":"ref24","article-title":"DSSD: Deconvolutional single shot detector","author":"fu","year":"2017","journal-title":"arXiv 1701 06659"},{"key":"ref23","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00401"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2910529"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00985"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00712"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_26"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref4","first-page":"21","article-title":"SSD: Single shot MultiBox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref3","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_33"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.330"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.440"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00409"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206532"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2980876"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref43","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/76\/9973795\/9474502-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9973795\/09474502.pdf?arnumber=9474502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:12:30Z","timestamp":1672081950000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9474502\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":50,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2021.3094533","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}