{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:18:59Z","timestamp":1740169139283,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2961383","type":"journal-article","created":{"date-parts":[[2019,12,23]],"date-time":"2019-12-23T23:56:55Z","timestamp":1577145415000},"page":"185654-185665","source":"Crossref","is-referenced-by-count":3,"title":["Mixpred: Video Prediction Beyond Optical Flow"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9512-322X","authenticated-orcid":false,"given":"Jie","family":"Yan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2472-4324","authenticated-orcid":false,"given":"Guihe","family":"Qin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1597-1961","authenticated-orcid":false,"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3971-9341","authenticated-orcid":false,"given":"Yanhua","family":"Liang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2484-4043","authenticated-orcid":false,"given":"Qianyi","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"2017","journal-title":"arXiv 1706 08033"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"ref32","first-page":"1144","article-title":"Video-to-video synthesis","author":"wang","year":"2018","journal-title":"Proc Neural Inf Process Syst (NIPS)"},{"key":"ref31","article-title":"Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild","author":"sedaghat","year":"2016","journal-title":"arXiv 1612 03777"},{"key":"ref30","first-page":"5617","article-title":"Deep learning for precipitation nowcasting: A benchmark and a new model","author":"shi","year":"2017","journal-title":"Proc Neural Inf Process Syst (NIPS)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00275"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018794"},{"key":"ref35","article-title":"VideoFlow: A flow-based generative model for video","author":"kumar","year":"2019","journal-title":"arXiv 1903 01434"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00280"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref11","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Neural Inf Process Syst (NIPS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref15","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00048"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2008.4621152"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.194"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref6","first-page":"5693","article-title":"Deep high-resolution representation learning for human pose estimation","author":"sun","year":"2019","journal-title":"Proc IEEE Int Conf Comput Vis (CVPR)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref5","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00251"},{"key":"ref2","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"william","year":"2016","journal-title":"arXiv 1605 08104"},{"key":"ref9","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"Proc Neural Inf Process Syst (NIPS)"},{"key":"ref1","article-title":"Deep multi-scale video prediction beyond mean square error","author":"michael","year":"2015","journal-title":"arXiv 1511 05440"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25446-8_4"},{"key":"ref22","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref21","article-title":"ImageNet-trained CNNs are biased towards texture; Increasing shape bias improves accuracy and robustness","author":"geirhos","year":"2018","journal-title":"arXiv 1811 12231"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.281"},{"key":"ref23","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_51"},{"key":"ref25","first-page":"4268","article-title":"Temporal coherency based criteria for predicting video frames using deep multi-stage generative adversarial networks","author":"bhattacharjee","year":"2017","journal-title":"Proc Neural Inf Process Syst (NIPS)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08938785.pdf?arnumber=8938785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:31:19Z","timestamp":1641987079000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8938785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2961383","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}