Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Deep generative video prediction | |
Yu, Tingzhao1,2; Wang, Lingfeng1,3; Gu, Huxiang1; Xiang, Shiming1; Pan, Chunhong1 | |
发表期刊 | PATTERN RECOGNITION LETTERS |
2018-07-15 | |
卷号 | 110期号:1页码:58-65 |
文章类型 | Article |
摘要 | Video prediction plays a fundamental role in video analysis and pattern recognition. However, the generated future frames are often blurred, which are not sufficient for further research. To overcome this obstacle, this paper proposes a new deep generative video prediction network under the framework of generative adversarial nets. The network consists of three components: a motion encoder, a frame generator and a frame discriminator. The motion encoder receives multiple frame differences (also known as Eulenan motion) as input and outputs a global video motion representation. The frame generator is a pseudo-reverse two-stream network to generate the future frame. The frame discriminator is a discriminative 3D convolution network to determine whether the given frame is derived from the true future frame distribution or not. The frame generator and frame discriminator train jointly in an adversarial manner until a Nash equilibrium. Motivated by theories on color filter array, this paper also designs a novel cross channel color gradient (3CG) loss as a guidance of deblurring. Experiments on two state-of-the-art data sets demonstrate that the proposed network is promising. (C) 2018 Elsevier B.V. All rights reserved. |
关键词 | Video Prediction Two Stream Adversarial Training Convlstm |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1016/j.patrec.2018.03.027 |
关键词[WOS] | SURVEILLANCE |
收录类别 | SCI |
语种 | 英语 |
项目资助者 | National Natural Science Foundation of China(61403376 ; Beijing Natural Science Foundation(4162064) ; Open Research Fund of Hunan Provincial Key Laboratory of Network Investigational Technology(2015HNWLFZ055) ; 61573352 ; 91646207 ; 91438105) |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000434780700009 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/22054 |
专题 | 模式识别国家重点实验室_先进时空数据分析与学习 |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 101408, Peoples R China 3.Hunan Police Acad, Hunan Prov Key Lab Network Invest Technol, Changsha 410138, Hunan, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Yu, Tingzhao,Wang, Lingfeng,Gu, Huxiang,et al. Deep generative video prediction[J]. PATTERN RECOGNITION LETTERS,2018,110(1):58-65. |
APA | Yu, Tingzhao,Wang, Lingfeng,Gu, Huxiang,Xiang, Shiming,&Pan, Chunhong.(2018).Deep generative video prediction.PATTERN RECOGNITION LETTERS,110(1),58-65. |
MLA | Yu, Tingzhao,et al."Deep generative video prediction".PATTERN RECOGNITION LETTERS 110.1(2018):58-65. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
[Tsingzao]Deep Gener(2082KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论