{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:37:09Z","timestamp":1778344629261,"version":"3.51.4"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683008","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"2047-2051","source":"Crossref","is-referenced-by-count":18,"title":["Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks"],"prefix":"10.1109","author":[{"given":"Xiaofeng","family":"Mao","sequence":"first","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuefeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhong","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Xiong","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"He","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Xue","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461984"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462648"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462082"},{"key":"ref14","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"0","journal-title":"ISCA Workshop on Speech Synthesis"},{"key":"ref15","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref17","article-title":"Film: Visual reasoning with a general conditioning layer","author":"perez","year":"0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"ref19","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2016","journal-title":"arXiv preprint arXiv 1610 01292"},{"key":"ref4","article-title":"Language guided fashion image manipulation with feature-wise transformations","author":"g\u00fcnel","year":"2018","journal-title":"arXiv preprint arXiv 1808 02194"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2120"},{"key":"ref6","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.608"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00011","article-title":"Feature-wise transformations","author":"dumoulin","year":"2018","journal-title":"Distillation"},{"key":"ref7","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv preprint arXiv 1411 1784"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.186"},{"key":"ref1","article-title":"Language-based image editing with recurrent attentive models","author":"chen","year":"2017","journal-title":"arXiv preprint arXiv 1711 03890"},{"key":"ref9","article-title":"The Caltech-UCSD Birds-200-2011 Dataset","author":"wah","year":"2011","journal-title":"Tech Rep"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref21","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv preprint arXiv 1411 2539"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683008.pdf?arnumber=8683008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:37:50Z","timestamp":1736969870000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683008\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683008","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}