{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:19:30Z","timestamp":1740169170578,"version":"3.37.3"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"MIC\/SCOPE","award":["#181601001"],"award-info":[{"award-number":["#181601001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2995815","type":"journal-article","created":{"date-parts":[[2020,5,20]],"date-time":"2020-05-20T20:32:01Z","timestamp":1590006721000},"page":"96777-96786","source":"Crossref","is-referenced-by-count":7,"title":["Enhancing Cross-Modal Retrieval Based on Modality-Specific and Embedding Spaces"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0110-7208","authenticated-orcid":false,"given":"Rintaro","family":"Yanagi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4474-3995","authenticated-orcid":false,"given":"Ren","family":"Togo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5332-8112","authenticated-orcid":false,"given":"Takahiro","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1496-1761","authenticated-orcid":false,"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_41"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2775109"},{"key":"ref33","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc IEEE Int Conf Learn Represent"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.170"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2709749"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540000"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref36","article-title":"VSE: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017","journal-title":"arXiv 1707 05612"},{"key":"ref35","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/0470013192.bsa068"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.04.045"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2619088"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01280"},{"key":"ref21","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc IEEE Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01278"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref26","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"arXiv 1605 05396"},{"key":"ref25","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc IEEE Eur Conf Comput Vis"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref11","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","first-page":"217","article-title":"Learning what and where to draw","author":"reed","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref13","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref14","first-page":"1","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref16","article-title":"A comprehensive survey on cross-modal retrieval","author":"wang","year":"2016","journal-title":"arXiv 1607 06215"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1049"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref19","first-page":"1","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"geirhos","year":"2019","journal-title":"Proc IEEE Int Conf Learn Represent"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-013-0489-0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"ref9","first-page":"686","article-title":"Deep cross-modal projection learning for image-text matching","author":"zhang","year":"2018","journal-title":"Proc IEEE Eur Conf Comput Vis"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref42","article-title":"TAC-GAN–text conditioned auxiliary classifier generative adversarial network","author":"dash","year":"2017","journal-title":"arXiv 1703 06412"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09097176.pdf?arnumber=9097176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:52:11Z","timestamp":1639770731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9097176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2995815","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}