OPT OpenIR  > 光学影像学习与分析中心
Long-Short-Term Features for Dynamic Scene Classification
Huang, Yuanjun1,2; Cao, Xianbin1,2; Wang, Qi3,4; Zhang, Baochang5; Zhen, Xiantong1,2; Li, Xuelong6,7
Department光学影像学习与分析中心
2019-04
Source PublicationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN1051-8215;1558-2205
Volume29Issue:4Pages:1038-1047
Contribution Rank6
Abstract

Dynamic scene classification has been extensively studied in computer vision due to its widespread applications. The key to dynamic scene classification lies in jointly characterizing spatial appearance and temporal dynamics to achieve informative representation, which remains an outstanding task in the literature. In this paper, we propose a unified framework to extract spatial and temporal features for dynamic scene representation. More specifically, we deploy two variants of deep convolutional neural networks to encode spatial appearance and short-term dynamics into short-term deep features (STDF). Based on STDF, we propose using the autoregressive moving average model to extract long-term frequency features (LTFF). By combining STDF and LTFF, we establish the long-short-term feature (LSTF) representations of dynamic scenes. The LSTF characterizes both spatial and temporal patterns of dynamic scenes for comprehensive and information representation that enables more accurate classification. Extensive experiments on three-dynamic scene classification benchmarks have shown that the proposed LSTF achieves high performance and substantially surpasses the state-of-the-art methods.

KeywordDynamic scene classification long-short term feature long term frequency feature
DOI10.1109/TCSVT.2018.2823360
Indexed BySCI
Language英语
WOS IDWOS:000464149700010
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Cited Times:2[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/31374
Collection光学影像学习与分析中心
Corresponding AuthorCao, Xianbin
Affiliation1.Beihang Univ, Sch Elect & Informat Engn, Beijing 100191, Peoples R China
2.Minist Ind & Informat Technol China, Key Lab Adv Technol Near Space Informat Syst, Beijing 100031, Peoples R China
3.Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Shaanxi, Peoples R China
4.Northwestern Polytech Univ, Ctr OPT IMagery Anal & Learning, Xian 710072, Shaanxi, Peoples R China
5.Beihang Univ, Sch Automat Sci & Elect Engn, Beijing 100191, Peoples R China
6.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Shaanxi, Peoples R China
7.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
Recommended Citation
GB/T 7714
Huang, Yuanjun,Cao, Xianbin,Wang, Qi,et al. Long-Short-Term Features for Dynamic Scene Classification[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2019,29(4):1038-1047.
APA Huang, Yuanjun,Cao, Xianbin,Wang, Qi,Zhang, Baochang,Zhen, Xiantong,&Li, Xuelong.(2019).Long-Short-Term Features for Dynamic Scene Classification.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,29(4),1038-1047.
MLA Huang, Yuanjun,et al."Long-Short-Term Features for Dynamic Scene Classification".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 29.4(2019):1038-1047.
Files in This Item:
File Name/Size DocType Version Access License
Long-Short-Term Feat(2016KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Huang, Yuanjun]'s Articles
[Cao, Xianbin]'s Articles
[Wang, Qi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Huang, Yuanjun]'s Articles
[Cao, Xianbin]'s Articles
[Wang, Qi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huang, Yuanjun]'s Articles
[Cao, Xianbin]'s Articles
[Wang, Qi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Long-Short-Term Features for Dynamic Scene Classification.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.