{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:20:17Z","timestamp":1772554817909,"version":"3.50.1"},"reference-count":53,"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":"Ministry of Science and Technology of China","award":["#2020AAA0108405"],"award-info":[{"award-number":["#2020AAA0108405"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["#62206287"],"award-info":[{"award-number":["#62206287"]}],"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":["#11832001"],"award-info":[{"award-number":["#11832001"]}],"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":["#71621002"],"award-info":[{"award-number":["#71621002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3229960","type":"journal-article","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T18:41:11Z","timestamp":1671216071000},"page":"7867-7880","source":"Crossref","is-referenced-by-count":2,"title":["AnANet: Association and Alignment Network for Modeling Implicit Relevance in Cross-Modal Correlation Classification"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9794-7262","authenticated-orcid":false,"given":"Nan","family":"Xu","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyan","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Wenge Technology Company, Ltd, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruike","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2323-5091","authenticated-orcid":false,"given":"Wenji","family":"Mao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1272"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475190"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102918"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3073267"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2510329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951194"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301371"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210093"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tpc.1998.661632"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1108\/00220410310506303"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/1470357205055928"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502203"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2611388"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.4304\/tpls.4.7.1415-1420"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9168"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078991"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-019-00187-6"},{"key":"ref20","first-page":"1","article-title":"Equal but not the same: Understanding the implicit relationship between persuasive images and text","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zhang","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1469"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298889"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2894498"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991171"},{"key":"ref25","first-page":"570","article-title":"Cite: A corpus of image-text discourse relations","volume-title":"Proc. IEEE Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Alikhani","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.583"},{"key":"ref27","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1448"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6525"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2022.3169884"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00740"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3161832"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035277"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.349"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2019.2932406"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref41","first-page":"272","article-title":"Automatic image annotation using auxiliary text information","volume-title":"Proc. ACL-08: HLT","author":"Feng","year":"2008"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.123"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref46","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. IEEE North Amer. Chapter Assoc. Comput. Linguistics","author":"Devlin","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref49","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref51","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01026"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.11.026"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09991062.pdf?arnumber=9991062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:10:15Z","timestamp":1703031015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9991062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3229960","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}