Show simple item record

FieldValueLanguage
dc.contributor.authorChen, Xinyuan
dc.contributor.authorXu, Chang
dc.contributor.authorYang, Xiaokang
dc.contributor.authorTao, Dacheng
dc.date.accessioned2021-12-21T04:23:21Z
dc.date.available2021-12-21T04:23:21Z
dc.date.issued2020en_AU
dc.identifier.urihttps://hdl.handle.net/2123/27253
dc.description.abstractVideo prediction refers to predicting and generating future video frames given a set of consecutive frames. Conventional video prediction methods usually criticize the discrepancy between the ground-truth and predictions frame by frame. As the prediction error accumulates recursively, these methods would easily become out of control and are often confined to the short-term horizon. In this paper, we introduce a retrospection process to rectify the prediction errors beyond criticizing the future prediction. The introduced retrospection process is designed to look back what have been learned from the past and rectify the prediction deficiencies. To this end, we build a retrospection network to reconstruct the past frames given the currently predicted frames. A retrospection loss is introduced to push the retrospection frames being consistent with the observed frames, so that the prediction error is alleviated. On the other hand, an auxiliary route is built by reversing the flow of time and executing a similar retrospection. These two routes interact with each other to boost the performance of retrospection network and enhance the understanding of dynamics across frames, especially for the long-term horizon. An adversarial loss is employed to generate more realistic results in both prediction and retrospection process. In addition, the proposed method can be used to extend many state-of-the-art video prediction methods. Extensive experiments on the natural video dataset demonstrate the advantage of introducing the retrospection process for long-term video prediction.en_AU
dc.publisherIEEEen_AU
dc.relation.ispartofIEEE Transactions on Image Processingen_AU
dc.titleLong-Term Video Prediction via Criticization and Retrospectionen_AU
dc.typeArticleen_AU
dc.subject.asrc0801 Artificial Intelligence and Image Processingen_AU
dc.identifier.doi10.1109/TIP.2020.2998297
dc.type.pubtypeAuthor accepted manuscripten_AU
dc.relation.arcFL-170100117
dc.relation.arcDP-180103424
dc.relation.arcIH-180100002
dc.relation.arcDE-180101438
dc.rights.other© 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en_AU
usyd.facultySeS faculties schools::Faculty of Engineering::School of Computer Scienceen_AU
workflow.metadata.onlyNoen_AU


Show simple item record

Associated file/s

Associated collections

Show simple item record

There are no previous versions of the item available.