CASIA OpenIR  > 类脑智能研究中心
Enhancing Cross-View Object Classification by Feature-Based Transfer Learning
Yi Mo; Zhaoxiang Zhang; Yunhong Wang
2012-11-11
Conference NameInternational Conference on Pattern Recognition
Source PublicationICPR 2012
Conference Date11-15 November 2012
Conference PlaceTsukuba, Japan
AbstractObject classification is of vital importance to intelligent traffic surveillance. A big challenge is that shooting view changes in different scenes, which leads to sharp accuracy decrease since training and test samples do not follow the same distribution anymore. On the other hand, manual labeling training samples is time and labor consuming. We propose a feature-based transfer learning framework to gap the divergence of different domain distributions with scarce target view samples. Source view samples, following a different but relevant distribution, could be utilized to learn what a good classifier is like by structure learning. At the same time, small amount of target view samples could make a great contribution to reflect the target distribution. Experimental results indicate that our method outperforms traditional approaches when target samples are too scarce to build a strong classifier.
KeywordAccuracy Vectors Training Surveillance Joints Manuals Pattern Recognition
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/13261
Collection类脑智能研究中心
Corresponding AuthorZhaoxiang Zhang
Recommended Citation
GB/T 7714
Yi Mo,Zhaoxiang Zhang,Yunhong Wang. Enhancing Cross-View Object Classification by Feature-Based Transfer Learning[C],2012.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yi Mo]'s Articles
[Zhaoxiang Zhang]'s Articles
[Yunhong Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yi Mo]'s Articles
[Zhaoxiang Zhang]'s Articles
[Yunhong Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yi Mo]'s Articles
[Zhaoxiang Zhang]'s Articles
[Yunhong Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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