{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:32:25Z","timestamp":1770917545037,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AME Programmatic Funding Scheme","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3154154","type":"journal-article","created":{"date-parts":[[2022,2,24]],"date-time":"2022-02-24T20:25:00Z","timestamp":1645734300000},"page":"3006-3016","source":"Crossref","is-referenced-by-count":15,"title":["Learning by Imagination: A Joint Framework for Text-Based Image Manipulation and Change Captioning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5863-3685","authenticated-orcid":false,"given":"Kenan E.","family":"Ak","sequence":"first","affiliation":[{"name":"Visual Intelligence, Institute for Infocomm Research, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7224-6726","authenticated-orcid":false,"given":"Ying","family":"Sun","sequence":"additional","affiliation":[{"name":"Visual Intelligence, Institute for Infocomm Research, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4103-3824","authenticated-orcid":false,"given":"Joo Hwee","family":"Lim","sequence":"additional","affiliation":[{"name":"Visual Intelligence, Institute for Infocomm Research, Singapore"}]}],"member":"263","reference":[{"key":"ref57","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.608"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.07.019"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191228"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref14","first-page":"42","article-title":"Text-adaptive generative adversarial networks: Manipulating images with natural language","author":"nam","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3059514"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988435"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00186"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.42"},{"key":"ref16","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"wah","year":"2011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1436"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref50","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref48","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref41","first-page":"1893","article-title":"Text as neural operator: Image manipulation by text instruction","author":"zhang","year":"0","journal-title":"Proc 29th ACM Int Conf on Multimedia"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21236\/ADA164453"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf on Learn Representations"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.127"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654948"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00804"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00379"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01040"},{"key":"ref35","article-title":"Language guided fashion image manipulation with feature-wise transformations","author":"g\u00fcnel","year":"0","journal-title":"Proc Eur Conf Comput Vis (ECCV) Workshops"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.186"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8804285"},{"key":"ref75","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref30","first-page":"217","article-title":"Learning what and where to draw","author":"reed","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref76","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Proc Text Summarization Branches Out"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref39","article-title":"Learn, imagine and create: Text-to-image generation from prior knowledge","author":"qiao","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref70","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref73","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf on Learn Representations"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref68","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054681"},{"key":"ref67","article-title":"Geometric GAN","author":"lim","year":"2017"},{"key":"ref23","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00787"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9734-5"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.6"},{"key":"ref66","article-title":"Lr-Gan: Layered recursive generative adversarial networks for image generation","author":"yang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.149"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_50"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/36.843009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01064"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506508"},{"key":"ref29","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018142"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00275"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_34"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09720958.pdf?arnumber=9720958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:02:13Z","timestamp":1693245733000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9720958\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3154154","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}