{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T16:08:40Z","timestamp":1772208520702,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"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":["61771329"],"award-info":[{"award-number":["61771329"]}],"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":["61632018"],"award-info":[{"award-number":["61632018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin","doi-asserted-by":"publisher","award":["19JCYBJC16000"],"award-info":[{"award-number":["19JCYBJC16000"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1109\/tcyb.2020.2985716","type":"journal-article","created":{"date-parts":[[2020,5,4]],"date-time":"2020-05-04T19:36:26Z","timestamp":1588620986000},"page":"1086-1097","source":"Crossref","is-referenced-by-count":43,"title":["SMAN: Stacked Multimodal Attention Network for Cross-Modal Image\u2013Text Retrieval"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2197-3739","authenticated-orcid":false,"given":"Zhong","family":"Ji","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6098-4772","authenticated-orcid":false,"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]},{"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Data Science Group, University of Warwick, Coventry, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2705068"},{"key":"ref2","first-page":"4601","article-title":"Linking image and text with 2-way nets","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Aviv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2879846"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.149"},{"key":"ref6","first-page":"935","article-title":"VSE++: Improved visual-semantic embeddings","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Fartash"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref8","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gehring"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIEC.2019.8784597"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877122"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878970"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/124"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1601787"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953753"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2864987"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_24"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2904996"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref30","first-page":"1","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshop","author":"Kiros"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","first-page":"1","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683869"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3300939"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref41","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mao"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240712"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1044"},{"key":"ref47","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref48","first-page":"1","article-title":"Order-embeddings of images and language","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Vendrov"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240535"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref56","volume-title":"Dual-path convolutional image-text embedding","author":"Zheng","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00601"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.224"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2908774"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9714899\/09086164.pdf?arnumber=9086164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:28:44Z","timestamp":1704839324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9086164\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2]]},"references-count":64,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2020.2985716","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2]]}}}