@inproceedings{70c76fb1f01841be881079060eac901b,
title = "SME-net: Sparse motion estimation for parametric video prediction through reinforcement learning",
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.",
author = "Ho, {Yung Han} and Cho, {Chuan Yuan} and Jin, {Guo Lun} and Wen-Hsiao Peng",
year = "2019",
month = oct,
doi = "10.1109/ICCV.2019.01056",
language = "English",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "10461--10469",
booktitle = "Proceedings - 2019 International Conference on Computer Vision, ICCV 2019",
address = "美國",
note = "17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 ; Conference date: 27-10-2019 Through 02-11-2019",
}