{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T06:52:56Z","timestamp":1746600776362,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"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":[[2021,9,19]]},"DOI":"10.1109\/icip42928.2021.9506508","type":"proceedings-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T17:08:41Z","timestamp":1629738521000},"page":"2693-2697","source":"Crossref","is-referenced-by-count":2,"title":["Robust Multi-Frame Future Prediction By Leveraging View Synthesis"],"prefix":"10.1109","author":[{"given":"Kenan E.","family":"Ak","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research A*STAR,Singapore"}]},{"given":"Ying","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research A*STAR,Singapore"}]},{"given":"Joo Hwee","family":"Lim","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research A*STAR,Singapore"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1016\/j.neunet.2021.04.016"},{"key":"ref31","first-page":"84","article-title":"Statistical parametric speech synthesis incorporating generative adversarial networks","volume":"26","author":"saito","year":"2017","journal-title":"IEEE\/ACM"},{"key":"ref30","article-title":"An overview of voice conversion and its challenges: From statistical modeling to deep learning","author":"sisman","year":"2020","journal-title":"TASLP"},{"key":"ref37","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"MICCAI"},{"key":"ref36","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.21437\/Interspeech.2019-3232"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.21437\/Interspeech.2020-2014"},{"key":"ref10","first-page":"3213","article-title":"The cityscapes dataset for semantic urban scene understanding","author":"cordts","year":"2016","journal-title":"CVPR"},{"key":"ref11","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref12","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"srivastava","year":"2015","journal-title":"ICML"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","first-page":"1771","article-title":"Video pixel networks","author":"kalchbrenner","year":"2017","journal-title":"ICML PMLR"},{"key":"ref15","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CVPR.2018.00804"},{"key":"ref17","first-page":"4797","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"NeurIPS Curran Associates Inc"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ICCV.2017.244"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICCV.2019.01064"},{"key":"ref4","article-title":"Team vi-i2r technical report on epic-kitchens action anticipation challenge 2020","author":"sun","year":"2020","journal-title":"Tech Rep"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICCV.2017.608"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICCV.2019.00635"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1016\/j.patrec.2020.02.030"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CVPR.2019.00191"},{"key":"ref5","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"lotter","year":"2016","journal-title":"arXiv preprint arXiv 1605 08104"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref8","first-page":"4090","article-title":"Monocular neural image based rendering with continuous view control","author":"chen","year":"2019","journal-title":"ICCV"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR42600.2020.00749"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/CVPR.2019.00688"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1177\/0278364913491297"},{"key":"ref1","first-page":"443","article-title":"Is faster r-cnn doing well for pedestrian detection?","author":"zhang","year":"2016","journal-title":"ECCV"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref22","article-title":"Unsupervised learning of shape and pose with differentiable point clouds","author":"insafutdinov","year":"2018","journal-title":"arXiv preprint arXiv 1810 09076"},{"year":"2018","author":"wang","journal-title":"Video-to-Video Synthesis","key":"ref21"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref23","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv 1411 1784"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICIP40778.2020.9190723"},{"key":"ref25","article-title":"Incorporating reinforced adversarial learning in autoregressive image generation","author":"kenan","year":"2020","journal-title":"ECCV"}],"event":{"name":"2021 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2021,9,19]]},"location":"Anchorage, AK, USA","end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9506008\/9506009\/09506508.pdf?arnumber=9506508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T18:59:23Z","timestamp":1670353163000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9506508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icip42928.2021.9506508","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}