{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:27:08Z","timestamp":1759332428702,"version":"3.37.3"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["NeTS-1909185"],"award-info":[{"award-number":["NeTS-1909185"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412890","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"1336-1343","source":"Crossref","is-referenced-by-count":16,"title":["Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation"],"prefix":"10.1109","author":[{"given":"Bin","family":"Duan","sequence":"first","affiliation":[]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Hugo","family":"Latapie","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682970"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.106"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/0028-3932(73)90060-2"},{"key":"ref32","article-title":"Learning to forecast and refine residual motion for image-to-video generation","author":"zhao","year":"0","journal-title":"ECCV"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.135"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416270"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00017"},{"key":"ref36","article-title":"Taskonomy: Disentangling task transfer learning","author":"zamir","year":"0","journal-title":"CVPR"},{"journal-title":"One model to learn them all","year":"2017","author":"kaiser","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.26.5.1583"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00252"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869695"},{"key":"ref29","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"0","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.142"},{"key":"ref1","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"NeurIPS"},{"key":"ref20","article-title":"Video-to-video synthesis","author":"wang","year":"0","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00789"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref23","article-title":"Xinggan for person image generation","author":"tang","year":"0","journal-title":"ECCV"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref50","article-title":"Improved techniques for training gans","author":"salimans","year":"0","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00768"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682383"},{"key":"ref12","article-title":"Deep cross-modal audiovisual generation","author":"chen","year":"0","journal-title":"ACM Workshop on MMUA"},{"key":"ref13","article-title":"Cmcgan: A uniform framework for cross-modal visual-audio mutual generation","author":"hao","year":"0","journal-title":"AAAI"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref15","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"journal-title":"Conditional generative adversarial nets","year":"2014","author":"mirza","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.820201"},{"key":"ref19","first-page":"522","article-title":"Creating a multi-track classical musical performance dataset for multimodal music analysis: Challenges, insights, and applications","author":"li","year":"0","journal-title":"TMM"},{"key":"ref4","article-title":"Mc-gan: Multi-conditional generative adversarial network for image synthesis","author":"park","year":"0","journal-title":"BMVC"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.97"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3021789"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref49","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"heusel","year":"0","journal-title":"NeurIPS"},{"journal-title":"Storygan A sequential conditional gan for story visualization","year":"2018","author":"li","key":"ref9"},{"key":"ref46","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"MICCAI"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"ICLRE"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.188"},{"key":"ref41","article-title":"Dual generator generative adversarial networks for multi-domain image-to-image translation","author":"tang","year":"0","journal-title":"ACCV"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5244\/C.18.30"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995668"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412890.pdf?arnumber=9412890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:44Z","timestamp":1652197244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412890\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412890","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}