{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:31:14Z","timestamp":1772908274053,"version":"3.50.1"},"reference-count":54,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772535"],"award-info":[{"award-number":["61772535"]}],"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":["62072462"],"award-info":[{"award-number":["62072462"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4192028"],"award-info":[{"award-number":["4192028"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2020AAA0108600"],"award-info":[{"award-number":["2020AAA0108600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3092187","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T21:16:51Z","timestamp":1624915011000},"page":"3013-3024","source":"Crossref","is-referenced-by-count":10,"title":["Enhancing Neural Machine Translation With Dual-Side Multimodal Awareness"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0246-4330","authenticated-orcid":false,"given":"Yuqing","family":"Song","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7313-9703","authenticated-orcid":false,"given":"Shizhe","family":"Chen","sequence":"additional","affiliation":[{"name":"INRIA, Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6486-6020","authenticated-orcid":false,"given":"Qin","family":"Jin","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Luo","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Xie","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3709-5053","authenticated-orcid":false,"given":"Fei","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018207"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01086"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/685"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.731"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01073"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1400"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2101"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01275"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.118"},{"key":"ref13","first-page":"130","article-title":"Imagination improves multimodal translation","volume-title":"Int. Joint Conf. Natural Lang. Process.","author":"Elliott","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1642"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1105"},{"key":"ref16","article-title":"Multimodal attention for neural machine translation","author":"Caglayan","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1175"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2031"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1095"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1653"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6484"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413715"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2954750"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1422"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.400"},{"key":"ref29","first-page":"1","article-title":"Neural machine translation with universal visual representation","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.147"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1118"},{"key":"ref32","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref33","first-page":"1","article-title":"Sequence level training with recurrent neural networks","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Ranzato","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/p14-5010"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren","year":"2015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref40","first-page":"1","article-title":"VSE++ Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4718"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref46","first-page":"223","article-title":"A study of translation edit rate with targeted human annotation","volume-title":"Proc. 7th Assoc. Mach. Transl. Americas Conf.","author":"Snover","year":"2006"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4755"},{"key":"ref49","first-page":"176","article-title":"Better hypothesis testing for statistical machine translation: Controlling for optimizer instability","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics","author":"Clark","year":"2011"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref51","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3 rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref52","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Duvenaud","year":"2015"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073478"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09465713.pdf?arnumber=9465713","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T22:59:29Z","timestamp":1705013969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9465713\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3092187","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}