{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T06:11:53Z","timestamp":1769062313719,"version":"3.49.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1109\/access.2019.2952676","type":"journal-article","created":{"date-parts":[[2019,11,11]],"date-time":"2019-11-11T17:54:40Z","timestamp":1573494880000},"page":"169920-169930","source":"Crossref","is-referenced-by-count":3,"title":["Text-to-Image GAN-Based Scene Retrieval and Re-Ranking Considering Word Importance"],"prefix":"10.1109","volume":"7","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":"10.1109\/ICMLA.2006.50"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102396"},{"key":"ref33","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"szegedy","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref32","first-page":"2508","article-title":"GraphGAN: Graph representation learning with generative adversarial nets","author":"wang","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080786"},{"key":"ref30","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017","journal-title":"arXiv 1707 05612"},{"key":"ref37","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref35","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc IEEE Eur Conf Comput Vis"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","article-title":"Word2VisualVec: Image and video to sentence matching by visual feature prediction","author":"dong","year":"2016","journal-title":"arXiv 1604 06838"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2012.03.004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2539540"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5438-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.135"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2593653"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.389"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2568099"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref18","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"arXiv 1605 05396"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref4","first-page":"54","article-title":"Video scene retrieval using online video annotation","author":"masuda","year":"2007","journal-title":"Proc Annu Conf Jpn Soc Artif Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1006\/jvci.1999.0413"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-007-0109-8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2006.313044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2697824"},{"key":"ref7","first-page":"1","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01211664"},{"key":"ref9","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-013-0489-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_41"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref21","first-page":"217","article-title":"Learning what and where to draw","author":"reed","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-015-1935-7"},{"key":"ref23","article-title":"TAC-GAN—Text conditioned auxiliary classifier generative adversarial network","author":"dash","year":"2017","journal-title":"arXiv 1703 06412"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08895780.pdf?arnumber=8895780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:32:27Z","timestamp":1641987147000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8895780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2952676","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}