{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T20:26:22Z","timestamp":1767903982158,"version":"3.49.0"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"High-quality and Cutting-edge Disciplines Construction Project for Universities in Beijing","award":["GJ19013504"],"award-info":[{"award-number":["GJ19013504"]}]},{"name":"National Key Task Team Cultivation Project 2019","award":["CUC19ZD003"],"award-info":[{"award-number":["CUC19ZD003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3058425","type":"journal-article","created":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T10:39:30Z","timestamp":1613817570000},"page":"27638-27649","source":"Crossref","is-referenced-by-count":6,"title":["VSAM-Based Visual Keyword Generation for Image Caption"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1038-2618","authenticated-orcid":false,"given":"Suya","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9287-3639","authenticated-orcid":false,"given":"Yana","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2766-2031","authenticated-orcid":false,"given":"Zeyu","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohui","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref31","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref30","author":"yang","year":"2017","journal-title":"A Faster Pytorch Implementation of Faster R-CNN"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00898"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/science.1138071"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nrn755"},{"key":"ref16","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref18","first-page":"2361","article-title":"Review networks for caption generation","author":"yang","year":"2016","journal-title":"Proc NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00188"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref3","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"2011","journal-title":"Proc EMNLP"},{"key":"ref6","first-page":"1292","article-title":"Image description using visual dependency representations","author":"elliott","year":"2013","journal-title":"Proc EMNLP"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref5","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proc EACL"},{"key":"ref8","first-page":"220","article-title":"Composing simple image descriptions using Web-scale N-grams","author":"li","year":"2011","journal-title":"Proc CoNLL"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018650"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref21","first-page":"4133","article-title":"Image caption with global-local attention","author":"li","year":"2017","journal-title":"Proc AAAI"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/84"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09351979.pdf?arnumber=9351979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T20:30:23Z","timestamp":1662669023000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9351979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3058425","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}