{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T08:56:27Z","timestamp":1774947387481,"version":"3.50.1"},"reference-count":56,"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":[{"name":"National Administration of Traditional Chinese Medicine","award":["ZYYCXTD-D-202208"],"award-info":[{"award-number":["ZYYCXTD-D-202208"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3202690","type":"journal-article","created":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T20:53:18Z","timestamp":1661806398000},"page":"5984-5999","source":"Crossref","is-referenced-by-count":15,"title":["Image Captioning With Novel Topics Guidance and Retrieval-Based Topics Re-Weighting"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1796-344X","authenticated-orcid":false,"given":"Majjed","family":"Al-Qatf","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1301-3535","authenticated-orcid":false,"given":"Xingfu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1069-3993","authenticated-orcid":false,"given":"Ammar","family":"Hawbani","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9426-3415","authenticated-orcid":false,"given":"Amr","family":"Abdussalam","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2857-6979","authenticated-orcid":false,"given":"Saeed Hammod","family":"Alsamhi","sequence":"additional","affiliation":[{"name":"Insight Centre for Data Analytics, National University of Ireland, Galway, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2904878"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02734-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref53","first-page":"1112","article-title":"Hierarchical LSTMs with adaptive attention for visual captioning","volume":"42","author":"gao","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941820"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01418-6_18"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-019-04262-2"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1108\/00220410410560582"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2969330"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref19","first-page":"1","article-title":"Order-embeddings of images and language","author":"vendrov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3336495"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.07.008"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3460474"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3386725"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3394955"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928144"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004729"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976552"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011317"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3036860"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.103068"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2889922"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04587-x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2860287"},{"key":"ref6","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2628585"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855406"},{"key":"ref35","first-page":"1","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Proc Text Summarization Branches Out"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref31","author":"bird","year":"2009","journal-title":"Natural Language Processing with Python Analyzing Text with the Natural Language Toolkit"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref32","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3025757"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051099"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2931815"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref26","first-page":"1","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"maas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"ref22","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/592"},{"key":"ref28","first-page":"2641","article-title":"Flickr30 k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","author":"plummer","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref27","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"chen","year":"2014","journal-title":"Eur Conf Comput Vis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09869686.pdf?arnumber=9869686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T20:03:19Z","timestamp":1701115399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9869686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3202690","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}