{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:25:40Z","timestamp":1740101140963,"version":"3.37.3"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T00:00:00Z","timestamp":1661126400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T00:00:00Z","timestamp":1661126400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2019YFB1803400"],"award-info":[{"award-number":["2019YFB1803400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61925105,62171257"],"award-info":[{"award-number":["61925105,62171257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,22]]},"DOI":"10.1109\/mlsp55214.2022.9943394","type":"proceedings-article","created":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T20:39:35Z","timestamp":1668717575000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["From Object-Attribute-Relation Semantic Representation to Video Generation: A Multiple Variational Autoencoder Approach"],"prefix":"10.1109","author":[{"given":"Yiping","family":"Duan","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]},{"given":"Mingzhe","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]},{"given":"Lijia","family":"Wen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]},{"given":"Qianqian","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University,Hangzhou,China"}]},{"given":"Xiaoming","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPR.2019.00878"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPR.2018.00713"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICCV48922.2021.01606"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref14","first-page":"1","article-title":"Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models","author":"bond-taylor","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/IJCNN48605.2020.9207056"},{"key":"ref16","article-title":"Generating diverse high-fidelity images with VQ-VA E-2","volume":"abs 1906 446","author":"razavi","year":"2019","journal-title":"CoRR"},{"key":"ref17","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30 Annual Conference on Neural Information Processing Systems 2017"},{"key":"ref18","article-title":"U-net: Convolutional networks for biomedical image segmentation","volume":"abs 1505 4597","author":"ronneberger","year":"2015","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref4","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"ArXiv org"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1007\/978-3-030-01228-1_28"},{"key":"ref6","article-title":"Few-shot video-to-video synthesis","volume":"abs 1910 12713","author":"wang","year":"2019","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/MLSP52302.2021.9596412"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CVPR.2018.00753"},{"key":"ref7","article-title":"Video-to-video synthesis","volume":"abs 1808 6601","author":"wang","year":"2018","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/MCOM.001.2001239"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/JSTSP.2020.2968772"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICCV.2017.477"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ACCESS51619.2021.9563328"}],"event":{"name":"2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2022,8,22]]},"location":"Xi'an, China","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9943282\/9943306\/09943394.pdf?arnumber=9943394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T20:00:02Z","timestamp":1670875202000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9943394\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,22]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/mlsp55214.2022.9943394","relation":{},"subject":[],"published":{"date-parts":[[2022,8,22]]}}}