{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T09:18:13Z","timestamp":1754558293402,"version":"3.37.3"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["62272447"],"award-info":[{"award-number":["62272447"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing","doi-asserted-by":"publisher","award":["4212029","L222008"],"award-info":[{"award-number":["4212029","L222008"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Newton Prize 2019 China Award","award":["NP2PB\/100047"],"award-info":[{"award-number":["NP2PB\/100047"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3278474","type":"journal-article","created":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T18:02:10Z","timestamp":1685037730000},"page":"3136-3149","source":"Crossref","is-referenced-by-count":6,"title":["Fine-Grained Video Retrieval With Scene Sketches"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9746-3487","authenticated-orcid":false,"given":"Ran","family":"Zuo","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Human-Computer Interaction, Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8576-1201","authenticated-orcid":false,"given":"Xiaoming","family":"Deng","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Human-Computer Interaction, Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keqi","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Human-Computer Interaction, Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Human-Computer Interaction, Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-5680","authenticated-orcid":false,"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Informatics, Cardiff University, Cardiff, U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7733-6790","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"BNRist Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3999-7429","authenticated-orcid":false,"given":"Cuixia","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Human-Computer Interaction, Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5774-1916","authenticated-orcid":false,"given":"Yong-Jin","family":"Liu","sequence":"additional","affiliation":[{"name":"BNRist Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongan","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Human-Computer Interaction, Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2669095"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_26"},{"journal-title":"Pyscenedetect","year":"2014","key":"ref34"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00830"},{"journal-title":"bert-as-service","year":"2018","author":"xiao","key":"ref37"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2814344"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00522"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.592"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.93"},{"key":"ref33","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925954"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_15"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/2.910894"},{"journal-title":"Elements of Episodic Memory","year":"1983","author":"tulving","key":"ref1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2667710"},{"key":"ref39","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299108"},{"key":"ref38","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16312"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6941"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/266180.266382"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6993"},{"key":"ref25","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2190389"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_15"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_42"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025765"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014491"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2668904.2668940"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2335395"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.38"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459258"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2461466.2461510"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27355-1_44"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10136606.pdf?arnumber=10136606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T20:54:04Z","timestamp":1704833644000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10136606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3278474","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2023]]}}}