{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T04:06:14Z","timestamp":1772769974032,"version":"3.50.1"},"reference-count":60,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["62076100"],"award-info":[{"award-number":["62076100"]}],"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":["51767005"],"award-info":[{"award-number":["51767005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["D2210010"],"award-info":[{"award-number":["D2210010"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["D2200150"],"award-info":[{"award-number":["D2200150"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["D2201300"],"award-info":[{"award-number":["D2201300"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2017B050506004"],"award-info":[{"award-number":["2017B050506004"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Programs of Guangzhou","award":["201704030076"],"award-info":[{"award-number":["201704030076"]}]},{"name":"Science and Technology Programs of Guangzhou","award":["201707010223"],"award-info":[{"award-number":["201707010223"]}]},{"name":"Science and Technology Programs of Guangzhou","award":["201802010027"],"award-info":[{"award-number":["201802010027"]}]},{"name":"Science and Technology Programs of Guangzhou","award":["201902010046"],"award-info":[{"award-number":["201902010046"]}]},{"name":"Hong Kong Research grants Council, China","award":["C1031-18G"],"award-info":[{"award-number":["C1031-18G"]}]},{"name":"Hong Kong Polytechnic University, China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3074803","type":"journal-article","created":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T01:42:06Z","timestamp":1619055726000},"page":"2004-2017","source":"Crossref","is-referenced-by-count":44,"title":["Image Difference Captioning With Instance-Level Fine-Grained Feature Representation"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7691-347X","authenticated-orcid":false,"given":"Qingbao","family":"Huang","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1561-7436","authenticated-orcid":false,"given":"Yu","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4892-5235","authenticated-orcid":false,"given":"Jielong","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-789X","authenticated-orcid":false,"given":"Cai","family":"Yi","sequence":"additional","affiliation":[{"name":"School of Software engineering, South China University of Technology, Guangzhou, China"}]},{"given":"Hanyu","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4914-2934","authenticated-orcid":false,"given":"Ho-fung","family":"Leung","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing, Hong Kong Polytechnic University, Hong Kong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2938342"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.61"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9734-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298737"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2784560"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-004-1010-x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990539"},{"key":"ref8","article-title":"Tell-the-difference: Fine-grained visual descriptor via a discriminating referee","author":"Xu","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390679"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00435"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/744"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930041"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/693"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1436"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3361758.3361783"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2957513"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2931223"},{"key":"ref28","article-title":"Detection and description of change in visual streams","author":"Gilton","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_34"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2921655"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951226"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/563"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350943"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref44","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2020","journal-title":"in Proc. Int. Conf. Learn. Represent"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3003290"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/s20174761"},{"key":"ref47","first-page":"1564","article-title":"Bilinear attention networks","author":"Kim","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00431"},{"issue":"34","key":"ref49","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","volume-title":"Proc. Int. Conf. Knowl. Discov. Data Min.","volume":"96","author":"Ester","year":"1996"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref52","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Vaswani","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref56","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text summarization branches out","author":"Lin","year":"2004"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.451"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1387"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref60","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"in Int. Conf. Learn. Represent"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09410374.pdf?arnumber=9410374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:38:52Z","timestamp":1704843532000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9410374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3074803","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}