{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T04:32:33Z","timestamp":1769920353552,"version":"3.49.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1109\/icip.2019.8803177","type":"proceedings-article","created":{"date-parts":[[2019,8,26]],"date-time":"2019-08-26T15:32:48Z","timestamp":1566833568000},"page":"1825-1829","source":"Crossref","is-referenced-by-count":5,"title":["Scene Retrieval for Video Summarization Based on Text-to-Image gan"],"prefix":"10.1109","author":[{"given":"Rintaro","family":"Yanagi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ren","family":"Togo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":"ref30","article-title":"VideoSET: Video Summary Evaluation through Text","author":"yeung","year":"2014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.118"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5438-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2539540"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE.2018.8574734"},{"key":"ref14","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01228-1_41","article-title":"Semi-supervised FusedGAN for conditional image generation","author":"bodla","year":"2018"},{"key":"ref17","first-page":"217","article-title":"Learning what and where to draw","author":"reed","year":"2016","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref28","article-title":"VSE ++ : Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-007-0109-8"},{"key":"ref27","article-title":"Word2VisualVec: Image and video to sentence matching by visual feature prediction","author":"dong","year":"2016"},{"key":"ref3","first-page":"3177","article-title":"Merchant Venturers Building, and Woodland Road, “Video scene retrieval based on local region features","author":"anjulan","year":"2006","journal-title":"Proceeding of the IEEE International Conference on Image Processing"},{"key":"ref6","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 Transactions on Systems Man and Cybernetics Part C Applications and Reviews"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref5","first-page":"54","article-title":"Video scene retrieval using online video annotation","author":"masuda","year":"2007","journal-title":"Proceedings of the Annual Conference on Japanese Society of Artificial Intelligence"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298981"},{"key":"ref7","first-page":"3","article-title":"Query-focused extractive video summarization","author":"sharghi","year":"2016","journal-title":"Proceeding of the European Conference on Computer Vision"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-013-0489-0"},{"key":"ref9","article-title":"Query-conditioned three-player adversarial network for video summarization","author":"zhang","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2012.2215006"},{"key":"ref20","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"szegedy","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref22","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proceedings of the IEEE European Conference on Computer Vision"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref24","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"2012","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref26","first-page":"1","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref25","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014"}],"event":{"name":"2019 IEEE International Conference on Image Processing (ICIP)","location":"Taipei, Taiwan","start":{"date-parts":[[2019,9,22]]},"end":{"date-parts":[[2019,9,25]]}},"container-title":["2019 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8791230\/8799366\/08803177.pdf?arnumber=8803177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:33:35Z","timestamp":1658144015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8803177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icip.2019.8803177","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}