完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Ho, Yung-Han | en_US |
dc.contributor.author | Cho, Chuan-Yuan | en_US |
dc.contributor.author | Peng, Wen-Hsiao | en_US |
dc.contributor.author | Jin, Guo-Lun | en_US |
dc.date.accessioned | 2020-10-05T02:01:30Z | - |
dc.date.available | 2020-10-05T02:01:30Z | - |
dc.date.issued | 2019-01-01 | en_US |
dc.identifier.isbn | 978-1-7281-4803-8 | en_US |
dc.identifier.issn | 1550-5499 | en_US |
dc.identifier.uri | http://dx.doi.org/10.1109/ICCV.2019.01056 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/155286 | - |
dc.description.abstract | This paper leverages a classic prediction technique, known as parametric overlapped block motion compensation (POBMC), in a reinforcement learning framework for video prediction. Learning-based prediction methods with explicit motion models often suffer from having to estimate large numbers of motion parameters with artificial regularization. Inspired by the success of sparse motion-based prediction for video compression, we propose a parametric video prediction on a sparse motion field composed of few critical pixels and their motion vectors. The prediction is achieved by gradually refining the estimate of a future frame in iterative, discrete steps. Along the way, the identification of critical pixels and their motion estimation are addressed by two neural networks trained under a reinforcement learning setting. Our model achieves the state-of-the-art performance on CaltchPed, UCF101 and CIF datasets in one-step and multi-step prediction tests. It shows good generalization results and is able to learn well on small training data. | en_US |
dc.language.iso | en_US | en_US |
dc.title | SME-Net: Sparse Motion Estimation for Parametric Video Prediction through Reinforcement Learning | en_US |
dc.type | Proceedings Paper | en_US |
dc.identifier.doi | 10.1109/ICCV.2019.01056 | en_US |
dc.identifier.journal | 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) | en_US |
dc.citation.spage | 10461 | en_US |
dc.citation.epage | 10469 | en_US |
dc.contributor.department | 資訊工程學系 | zh_TW |
dc.contributor.department | Department of Computer Science | en_US |
dc.identifier.wosnumber | WOS:000548549205059 | en_US |
dc.citation.woscount | 0 | en_US |
顯示於類別: | 會議論文 |