Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Pseudo low rank video representation | |
Yu, Tingzhao1,2; Wang, Lingfeng1; Guo, Chaoxu1,2; Gu, Huxiang1; Xiang, Shiming1; Pan, Chunhong1 | |
发表期刊 | PATTERN RECOGNITION |
ISSN | 0031-3203 |
2019 | |
卷号 | 85期号:1页码:50-59 |
摘要 | Action recognition plays a fundamental role in computer vision and has drawn growing attention recently. This paper addresses this issue conditioned on extreme Low Resolution (abbreviated as eLR). Generally, eLR video is often susceptible to noise, thus extracting a robust representation is of great challenge. Besides, due to the limitation of video resolution, eLR video cannot be cropped or resized randomly, then it is inevitably complicated to design and to train a deep network for eLR video. This paper proposes a novel network for robust video representation by employing pseudo tensor low rank regularization. A new Video Low Rank Representation model (named VLRR) is first proposed to recover the inherent robust component of a given video, and then the recovered term is introduced to a convolutional Network (denoted pLRN) as an auxiliary pseudo Low Rank guidance. Benefitting from the auxiliary guidance, pLRN can learn an approximate low rank term end-to-end. Besides, this paper presents a new initialization strategy for eLR recognition neTwork based on Tensor factorization (dubbed TenneT). TenneT is data-driven and learns the convolutional kernels totally from the video distribution while without any back-propagation. It outperforms random initialization both in speed and accuracy. Experiments on benchmark datasets demonstrate the effectiveness and superiority of the proposed method. (C) 2018 Elsevier Ltd. All rights reserved. |
关键词 | Pseudo low rank Data driven Low resolution Action recognition |
DOI | 10.1016/j.patcog.2018.07.033 |
关键词[WOS] | ACTION RECOGNITION ; DECOMPOSITION |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61620106003] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61620106003] |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000447819300005 |
出版者 | ELSEVIER SCI LTD |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/22783 |
专题 | 模式识别国家重点实验室_先进时空数据分析与学习 |
通讯作者 | Yu, Tingzhao |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Yu, Tingzhao,Wang, Lingfeng,Guo, Chaoxu,et al. Pseudo low rank video representation[J]. PATTERN RECOGNITION,2019,85(1):50-59. |
APA | Yu, Tingzhao,Wang, Lingfeng,Guo, Chaoxu,Gu, Huxiang,Xiang, Shiming,&Pan, Chunhong.(2019).Pseudo low rank video representation.PATTERN RECOGNITION,85(1),50-59. |
MLA | Yu, Tingzhao,et al."Pseudo low rank video representation".PATTERN RECOGNITION 85.1(2019):50-59. |
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]Pseudo low(1456KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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