{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:35:05Z","timestamp":1761060905171,"version":"3.37.3"},"reference-count":59,"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.2019.2947409","type":"journal-article","created":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T19:23:13Z","timestamp":1571080993000},"page":"153183-153193","source":"Crossref","is-referenced-by-count":14,"title":["Query is GAN: Scene Retrieval With Attentional Text-to-Image Generative Adversarial Network"],"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"}]},{"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref33","article-title":"TAC-GAN—Text conditioned auxiliary classifier generative adversarial network","author":"dash","year":"2017","journal-title":"arXiv 1703 06412"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref31","first-page":"217","article-title":"Learning what and where to draw","author":"reed","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_41"},{"key":"ref37","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"article-title":"The caltech-UCSD birds-200-2011 dataset","year":"2011","author":"wah","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref28","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5438-7"},{"key":"ref29","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"arXiv 1605 05396"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-013-0489-0"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2237022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.07.012"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2876833"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2697824"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654948"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2905741"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2539540"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2709749"},{"key":"ref50","first-page":"1486","article-title":"Deep generative image models using a Laplacian pyramid of adversarial networks","author":"denton","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.728"},{"key":"ref59","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017","journal-title":"arXiv 1707 05612"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref55","article-title":"Text2Shape: Generating shapes from natural language by learning joint embeddings","author":"chen","year":"2018","journal-title":"arXiv 1803 08495"},{"key":"ref54","first-page":"2255","article-title":"Generative adversarial positive-unlabeled learning","author":"hou","year":"2018","journal-title":"Proc Int Joint Artif Intell Conf"},{"key":"ref53","first-page":"34","article-title":"MuseGAN: Multi-track sequential generative adversarial networks for symbolic music generation and accompaniment","author":"dong","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296985"},{"key":"ref10","first-page":"1","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2006.313044"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-007-0109-8"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1109\/TSMCC.2011.2109710","article-title":"A survey on visual content-based video indexing and retrieval","volume":"41","author":"hu","year":"2011","journal-title":"IEEE Trans Syst Man Cybern C Appl Rev"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2568099"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896515"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2895511"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1762","DOI":"10.1109\/TMM.2018.2885237","article-title":"Video big data retrieval over media cloud: A context-aware online learning approach","volume":"21","author":"wu","year":"2019","journal-title":"IEEE Trans Multimedia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2425216"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1006\/jvci.1999.0413"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2821959"},{"key":"ref8","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.04.045"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref9","article-title":"Word2VisualVec: Image and video to sentence matching by visual feature prediction","author":"dong","year":"2016","journal-title":"arXiv 1604 06838"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_35"},{"key":"ref48","article-title":"StarGAN: Unified generative adversarial networks for multi-domain image-to-image translation","author":"choi","year":"2017","journal-title":"arXiv 1711 09020"},{"key":"ref47","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08868179.pdf?arnumber=8868179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:39:42Z","timestamp":1628624382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8868179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2947409","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}