{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:00:24Z","timestamp":1732039224472,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"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":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093308","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"3017-3031","source":"Crossref","is-referenced-by-count":2,"title":["Jointly Trained Image and Video Generation using Residual Vectors"],"prefix":"10.1109","author":[{"given":"Yatin","family":"Dandi","sequence":"first","affiliation":[]},{"given":"Aniket","family":"Das","sequence":"additional","affiliation":[]},{"given":"Soumye","family":"Singhal","sequence":"additional","affiliation":[]},{"given":"Vinay P.","family":"Namboodiri","sequence":"additional","affiliation":[]},{"given":"Piyush","family":"Rai","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"?-vae:learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref11","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref13","first-page":"17551758","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"The Journal of Machine Learning Research"},{"key":"ref14","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref15","article-title":"Videoflow: A flow-based generative model for video","author":"kumar","year":"2019","journal-title":"arXiv preprint arXiv 190301434"},{"key":"ref16","article-title":"Stochastic adversarial video prediction","author":"lee","year":"2018","journal-title":"arXiv preprint arXiv 180401523"},{"key":"ref17","article-title":"Disentangled sequential autoencoder","author":"li","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref18","article-title":"Deep multiscale video prediction beyond mean square error","author":"mathieu","year":"2016","journal-title":"International Conference on Learning Representations (ICLR("},{"key":"ref19","article-title":"Action-conditional video prediction using deep networks in atari","author":"oh","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2011.07.002"},{"key":"ref4","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref27","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00770"},{"key":"ref6","article-title":"Stochastic video generation with a learned prior","author":"denton","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref5","article-title":"Unsupervised learning of disentangled representations from video","author":"denton","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref8","article-title":"Actions as space-time shapes","author":"gorelick","year":"2005","journal-title":"IEEE International Conference on Computer Vision (ICCV)"},{"key":"ref7","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref2","article-title":"Stochastic variational video prediction","author":"babaeizadeh","year":"2017","journal-title":"arXiv preprint arXiv 171011252"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_28"},{"key":"ref1","article-title":"The mug facial expression database","author":"aifanti","year":"2010","journal-title":"Proc 8th Int Workshop Image Analy Multimedia Interactive Services (WIAMIS)"},{"key":"ref20","article-title":"Video (language) modeling: a baseline for generative models of natural videos","author":"ranzato","year":"2014","journal-title":"arXiv preprint arXiv 14126604"},{"key":"ref22","article-title":"Improved techniques for training gans","author":"salimans","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref23","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"srivastava","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref26","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref25","article-title":"Towards accurate generative models of video: A new metric and challenges","author":"unterthiner","year":"2018","journal-title":"arXiv preprint arXiv 1812 01717"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","start":{"date-parts":[[2020,3,1]]},"location":"Snowmass Village, CO, USA","end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093308.pdf?arnumber=9093308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:18:25Z","timestamp":1656602305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093308","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}