CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Unsupervised Cross-Dataset Transfer Learning for Person Re-identification
Peng PX(彭佩玺)1; Tao Xiang3; Wang YW(王耀威)4; Massimiliano Pontil2; Huang TJ(黄铁军)1; Tian YH(田永鸿)1
2016
Conference NameComputer Vision & Pattern Recognition
Conference Date2016 .07
Conference PlaceLas Vegas, NV, USA
AbstractMost existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. This severely limits their scalability in realworld applications. To overcome this limitation, we develop a novel cross-dataset transfer learning approach to learn a discriminative representation. It is unsupervised in the sense that the target dataset is completely unlabelled. Specifically, we present an multi-task dictionary learning method which is able to learn a dataset-shared but targetdata-biased representation. Experimental results on five benchmark datasets demonstrate that the method significantly outperforms the state-of-the-art.
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20219
Collection模式识别国家重点实验室_视频内容安全
Affiliation1.北京大学
2.University College London
3.Queen Mary, Univ. of London,
4.北京理工大学
Recommended Citation
GB/T 7714
Peng PX,Tao Xiang,Wang YW,et al. Unsupervised Cross-Dataset Transfer Learning for Person Re-identification[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
UnsupervisedCross-Da(349KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Peng PX(彭佩玺)]'s Articles
[Tao Xiang]'s Articles
[Wang YW(王耀威)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Peng PX(彭佩玺)]'s Articles
[Tao Xiang]'s Articles
[Wang YW(王耀威)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Peng PX(彭佩玺)]'s Articles
[Tao Xiang]'s Articles
[Wang YW(王耀威)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: UnsupervisedCross-DatasetTransferLearningforPersonRe-identification.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

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