智能系统学报2018，Vol.13Issue(1)：85-96,12.DOI:10.11992/tis.201707032
基于深度学习的视频预测研究综述
Review of deep learning-based video prediction
摘要
Abstract
In recent years, deep learning algorithms have made significant achievements on various supervised learning problems, with their accuracy, efficiency, and intelligence outperforming traditional machine learning algorithms, in some instances even beyond human capability. Currently, deep learning researchers are gradually turning their interests from supervised learning to the areas of reinforcement learning, weakly supervised learning, and unsupervised learning. Video prediction algorithms have developed rapidly in the last two years due to its capability of using a large amount of unlabeled and naturalistic data to construct the forthcoming video as well as its widespread application value in decision making, autonomous driving, video comprehension, and other fields. In this paper, we review the development back-ground of the video prediction algorithms and the history of deep learning. Then, we briefly introduce the human activity, object movement, and trajectory prediction algorithms, with a focus on mainstream video prediction methods that are based on deep learning. We summarize current problems related to this research and consider the future prospects of this field.关键词
视频预测/深度学习/无监督学习/运动预测/动作识别/卷积神经网络/递归神经网络/自编码器Key words
video prediction/deep learning/unsupervised learning/motion prediction/action recognition/convolution neural network/recurrent neural network/auto encoder分类
信息技术与安全科学引用本文复制引用
莫凌飞,蒋红亮,李煊鹏..基于深度学习的视频预测研究综述[J].智能系统学报,2018,13(1):85-96,12.基金项目
国家十二五科技支撑计划重点项目(2015BAG09B01). （2015BAG09B01）
