{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T07:04:54Z","timestamp":1751094294548,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T00:00:00Z","timestamp":1716076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T00:00:00Z","timestamp":1716076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,19]]},"DOI":"10.1109\/iscas58744.2024.10557902","type":"proceedings-article","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T17:22:52Z","timestamp":1719940972000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Audio-Visual Cross-Modal Generation with Multimodal Variational Generative Model"],"prefix":"10.1109","author":[{"given":"Zhubin","family":"Xu","sequence":"first","affiliation":[{"name":"Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianlei","family":"Wang","sequence":"additional","affiliation":[{"name":"Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dekang","family":"Liu","sequence":"additional","affiliation":[{"name":"Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinghan","family":"Hu","sequence":"additional","affiliation":[{"name":"Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanqiang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Huaqiao University,School of Engineering and School of Information Science and Engineering,Fujian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiuwen","family":"Cao","sequence":"additional","affiliation":[{"name":"Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2460697"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00278"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682513"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892863"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref9"},{"key":"ref10","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"International conference on machine learning","author":"Van Den Oord"},{"key":"ref12","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11040"},{"article-title":"Joint multimodal learning with deep generative models","year":"2016","author":"Suzuki","key":"ref15"},{"key":"ref16","article-title":"Multimodal generative models for scalable weakly-supervised learning","volume":"31","author":"Wu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Variational mixture-of-experts autoen-coders for multi-modal deep generative models","volume":"32","author":"Shi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.11.019"},{"article-title":"Improving bi-directional generation between different modalities with variational autoencoders","year":"2018","author":"Suzuki","key":"ref19"},{"article-title":"Multimodal generative models for compositional representation learning","year":"2019","author":"Wu","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref22","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"International conference on machine learning","author":"Larsen"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"Warden","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref26","first-page":"9179","article-title":"Simple and effective vae training with calibrated decoders","volume-title":"International Conference on Machine Learning","author":"Rybkin"}],"event":{"name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2024,5,19]]},"location":"Singapore, Singapore","end":{"date-parts":[[2024,5,22]]}},"container-title":["2024 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10557746\/10557828\/10557902.pdf?arnumber=10557902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T06:41:03Z","timestamp":1719988863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10557902\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,19]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iscas58744.2024.10557902","relation":{},"subject":[],"published":{"date-parts":[[2024,5,19]]}}}