{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T04:44:04Z","timestamp":1768711444952,"version":"3.49.0"},"reference-count":62,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1406603"],"award-info":[{"award-number":["2020YFB1406603"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19A2057"],"award-info":[{"award-number":["U19A2057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["61525206"],"award-info":[{"award-number":["61525206"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK3480000008"],"award-info":[{"award-number":["WK3480000008"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2020.3046855","type":"journal-article","created":{"date-parts":[[2020,12,23]],"date-time":"2020-12-23T20:33:50Z","timestamp":1608755630000},"page":"103-115","source":"Crossref","is-referenced-by-count":18,"title":["Focus Your Attention: A Focal Attention for Multimodal Learning"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3307-9558","authenticated-orcid":false,"given":"Chunxiao","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-9145","authenticated-orcid":false,"given":"An-An","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877122"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2921876"},{"key":"ref32","article-title":"Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2272919"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref35","first-page":"1564","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume":"29","author":"lu","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref60","article-title":"Caltech-ucsd birds-200-2011 dataset","author":"wah","year":"2011"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.374"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00757"},{"key":"ref29","first-page":"8334","article-title":"Learning conditioned graph structures for interpretable visual question answering","author":"norcliffe-brown","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2890628"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref56","article-title":"Deep captioning with multimodal recurrent neural networks","author":"mao","year":"2014","journal-title":"CoRR"},{"key":"ref55","first-page":"740?755","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Eur Conf Comput Vis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2111363"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350993"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2508146"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2535864"},{"key":"ref12","first-page":"2121?2129","article-title":"DeVise: A deep visual-semantic embedding model","author":"frome","year":"0","journal-title":"NIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240712"},{"key":"ref14","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Brit Mach Vis Conf"},{"key":"ref15","first-page":"2048?2057","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00593"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"ref19","first-page":"5659","article-title":"SCA-CNN: Spatial and channel-Wise attention in convolutional networks for image captioning","author":"long","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref4","first-page":"2672","article-title":"Generative adversarial networks","volume":"3","author":"goodfellow","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref6","first-page":"1062?1075","article-title":"Cross-modality microblog sentiment prediction via bi-layer multimodal hypergraph learning","volume":"21","author":"ji","year":"2018","journal-title":"IEEE Trans Multimedia"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref8","first-page":"1889?1897","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref49","first-page":"13063","article-title":"Unified language model pre-training for natural language understanding and generation","author":"dong","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2663324"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref46","first-page":"1947?1962","article-title":"Stackgan: Realistic image synthesis with stacked generative adversarial networks","volume":"41","author":"zhang","year":"2018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref48","article-title":"Generating images from captions with attention","author":"mansimov","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018312"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240521"},{"key":"ref41","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2015","journal-title":"CoRR"},{"key":"ref44","first-page":"1?1","article-title":"Modality-specific cross-modal similarity measurement with recurrent attention network","author":"peng","year":"2017","journal-title":"IEEE Trans Image Process"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09305249.pdf?arnumber=9305249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T20:49:53Z","timestamp":1649710193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9305249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3046855","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}