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
DOI10.1016/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
被引频次:12[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/22054
专题多模态人工智能系统全国重点实验室_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 下载所有文件
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 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yu, Tingzhao]的文章
[Wang, Lingfeng]的文章
[Gu, Huxiang]的文章
百度学术
百度学术中相似的文章
[Yu, Tingzhao]的文章
[Wang, Lingfeng]的文章
[Gu, Huxiang]的文章
必应学术
必应学术中相似的文章
[Yu, Tingzhao]的文章
[Wang, Lingfeng]的文章
[Gu, Huxiang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: [Tsingzao]Deep Generative Video Prediction.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

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。