{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T05:03:19Z","timestamp":1748494999566},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9052918","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"4392-4396","source":"Crossref","is-referenced-by-count":3,"title":["Spectrogram Analysis Via Self-Attention for Realizing Cross-Model Visual-Audio Generation"],"prefix":"10.1109","author":[{"given":"Huadong","family":"Tan","sequence":"first","affiliation":[]},{"given":"Guang","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Pengcheng","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yanxiang","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref11","first-page":"570","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Self-attention generative adversarial networks","year":"2018","author":"zhang","key":"ref16"},{"article-title":"cgans with projection discriminator","year":"2018","author":"miyato","key":"ref17"},{"article-title":"Geometric gan","year":"2017","author":"lim","key":"ref18"},{"article-title":"Spectral normalization for generative adversarial networks","year":"2018","author":"miyato","key":"ref19"},{"key":"ref4","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"article-title":"Generative adversarial text to image synthesis","year":"2016","author":"reed","key":"ref2"},{"key":"ref1","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"article-title":"Conditional generative adversarial nets","year":"2014","author":"mirza","key":"ref9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12329","article-title":"Cmcgan: A uniform framework for cross-modal visual-audio mutual generation","author":"hao","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09052918.pdf?arnumber=9052918","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T15:27:50Z","timestamp":1696001270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9052918\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9052918","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}