{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T21:55:45Z","timestamp":1758405345234,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"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":[[2020,10]]},"DOI":"10.1109\/icip40778.2020.9191228","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T20:45:18Z","timestamp":1601498718000},"page":"1601-1605","source":"Crossref","is-referenced-by-count":8,"title":["Learning Cross-Modal Representations for Language-Based Image Manipulation"],"prefix":"10.1109","author":[{"given":"E.Ak","family":"Kenan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joo Hwee","family":"Lim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003939"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023162"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-34"},{"key":"ref30","first-page":"84","article-title":"Statistical parametric speech synthesis incorporating generative adversarial networks","volume":"26","author":"saito","year":"2017","journal-title":"IEEE\/ACM"},{"journal-title":"The Caltech-UCSD Birds-200-2011 Dataset","year":"2011","author":"wah","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3232"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639507"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.608"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01040"},{"key":"ref13","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Language guided fashion image manipulation with feature-wise transformations","author":"g\u00fcnel","year":"2018","journal-title":"arXiv preprint arXiv 1808 04761"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00787"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref28","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"arXiv 1605 05396"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00804"},{"key":"ref27","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"arXiv 1511 06434"},{"key":"ref3","article-title":"Fashion-searchnet: Fashion search with attribute manipulation","author":"ak","year":"2018","journal-title":"ECCVW"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.07.019"},{"key":"ref29","first-page":"217","article-title":"Learning what and where to draw","author":"reed","year":"2016","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00186"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.02.030"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01064"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00379"},{"key":"ref9","article-title":"Large scale gan training for high fidelity natural image synthesis","author":"brock","year":"2018","journal-title":"arXiv preprint arXiv 1809 11096"},{"journal-title":"Deep Learning Approaches for Attribute Manipulation and Text-to-Image Synthesis","year":"2019","author":"ak","key":"ref1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.186"},{"key":"ref20","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv preprint arXiv 1411 2539"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref22","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv 1411 1784"},{"key":"ref21","article-title":"Geometric gan","author":"lim","year":"2017","journal-title":"arXiv 1705 02894"},{"key":"ref42","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"2018","journal-title":"arXiv preprint arXiv 1805 08318"},{"key":"ref24","first-page":"42","article-title":"Text-adaptive generative adversarial networks: manipulating images with natural language","author":"nam","year":"2018","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8804285"},{"key":"ref23","article-title":"Spectral arXiv preprint normalization for generative adversarial networks","author":"miyato","year":"2018","journal-title":"arXiv preprint arxiv 1802 05807"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.42"}],"event":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2020,10,25]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2020,10,28]]}},"container-title":["2020 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9184803\/9190635\/09191228.pdf?arnumber=9191228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:14:28Z","timestamp":1656375268000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9191228\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icip40778.2020.9191228","relation":{},"subject":[],"published":{"date-parts":[[2020,10]]}}}