{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:38:42Z","timestamp":1783183122927,"version":"3.54.6"},"reference-count":63,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Grant-in-Aid for Young Scientists","award":["#19K20343"],"award-info":[{"award-number":["#19K20343"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2021.3138719","type":"journal-article","created":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T21:22:55Z","timestamp":1640726575000},"page":"244-259","source":"Crossref","is-referenced-by-count":23,"title":["Word-Region Alignment-Guided Multimodal Neural Machine Translation"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0958-8253","authenticated-orcid":false,"given":"Yuting","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mamoru","family":"Komachi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoyuki","family":"Kajiwara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9848-6384","authenticated-orcid":false,"given":"Chenhui","family":"Chu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever","year":"2014"},{"issue":"abs\/1409.0473","key":"ref2","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2346"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4718"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6402"},{"key":"ref6","article-title":"Multi-language image description with neural sequence models","volume":"abs\/1510.04709","author":"Elliott","year":"2015"},{"key":"ref7","first-page":"130","article-title":"Imagination improves multimodal translation","volume-title":"Proc. 8th Int. Joint Conf. Natural Lang. Process.","author":"Elliott","year":"2017"},{"key":"ref8","article-title":"Neural machine translation with latent semantic of image and text","volume":"abs\/1611.08459","author":"Toyama","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1105"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4746"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"issue":"abs\/1609.03976","key":"ref12","article-title":"Multimodal attention for neural machine translation","author":"Caglayan","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1175"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1095"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1422"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6484"},{"key":"ref19","first-page":"105","article-title":"Double attention-based multimodal neural machine translation with semantic image regions","volume-title":"Proc. 22nd Annu. Conf. Eur. Assoc. Mach. Transl.","author":"Zhao","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref22","first-page":"4204","article-title":"A visually-grounded parallel corpus with phrase-to-region linking","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Nakayama","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2360"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2358"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2031"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6326"},{"issue":"abs\/1807.11605","key":"ref28","article-title":"Doubly attentive transformer machine translation","author":"Arslan","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1329"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6439"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1653"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1400"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1642"},{"key":"ref34","first-page":"1","article-title":"Neural machine translation with universal visual representation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.380"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413715"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.400"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-6406"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.452"},{"key":"ref41","first-page":"6847","article-title":"Aligning visual regions and textual concepts for semantic-grounded image representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.642"},{"issue":"abs\/2004.00849","key":"ref44","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref49","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"issue":"abs\/1810.06245","key":"ref52","article-title":"Bringing back simplicity and lightliness into neural image captioning","author":"Delbrouck","year":"2018"},{"issue":"abs\/1810.06233","key":"ref53","article-title":"UMONS submission for WMT18 multimodal translation task","author":"Delbrouck","year":"2018"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref55","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref60","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Koehn","year":"2004"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1515\/pralin-2017-0035"},{"key":"ref62","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref63","first-page":"944","article-title":"Automatic evaluation of translation quality for distant language pairs","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Isozaki","year":"2010"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09664333.pdf?arnumber=9664333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T21:48:29Z","timestamp":1705182509000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9664333\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3138719","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}