CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Multi-type attributes driven multi-camera person re-identification
Chi Su1; Shiliang Zhang1; Junliang Xing2; Wen Gao1; Qi Tian3
Source PublicationPattern Recognition
AbstractOne of the major challenges in person Re-Identification (ReID) is the inconsistent visual appearance of a person. Current works on visual feature and distance metric learning have achieved significant achievements, but still suffer from the limited robustness to pose variations, viewpoint changes, etc., and the high computational complexity. This makes person ReID among multiple cameras still challenging. This work is motivated to learn mid-level human attributes which are robust to visual appearance variations and could be used as efficient features for person matching. We propose a weakly supervised multi-type attribute learning framework which considers the contextual cues among attributes and progressively boosts the accuracy of attributes only using a limited number of labeled data. Specifically, this framework involves a three-stage training. A deep Convolutional Neural Network (dCNN) is first trained on an independent dataset labeled with attributes. Then it is fine-tuned on another dataset only labeled with person IDs using our defined triplet loss. Finally, the updated dCNN predicts attribute labels for the target dataset, which is combined with the independent dataset for the final round of fine-tuning. The predicted attributes, namely deep attributes exhibit promising generalization ability across different datasets. By directly using the deep attributes with simple Cosine distance, we have obtained competitive accuracy on four person ReID datasets. Experiments also show that a simple distance metric learning modular further boosts our method, making it outperform many recent works.
KeywordDeep Attributes Person Re-identification
Document Type期刊论文
Affiliation1.National Engineering Laboratory for Video Technology, Peking University, Beijing, China
2.National Laboratory of Pattern Recognition, Insititue of Automation, Chinese Academy of Sciences
3.Department of Computer Science, University of Texas at San Antonio, San Antonio, USA
Recommended Citation
GB/T 7714
Chi Su,Shiliang Zhang,Junliang Xing,et al. Multi-type attributes driven multi-camera person re-identification[J]. Pattern Recognition,2017(75):77-89.
APA Chi Su,Shiliang Zhang,Junliang Xing,Wen Gao,&Qi Tian.(2017).Multi-type attributes driven multi-camera person re-identification.Pattern Recognition(75),77-89.
MLA Chi Su,et al."Multi-type attributes driven multi-camera person re-identification".Pattern Recognition .75(2017):77-89.
Files in This Item: Download All
File Name/Size DocType Version Access License
PR18MultiTypeAttribu(3413KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chi Su]'s Articles
[Shiliang Zhang]'s Articles
[Junliang Xing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chi Su]'s Articles
[Shiliang Zhang]'s Articles
[Junliang Xing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chi Su]'s Articles
[Shiliang Zhang]'s Articles
[Junliang Xing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: PR18MultiTypeAttributesDrivenMultiCameraPersonReIdentification.pdf
Format: Adobe PDF
All comments (0)
No comment.

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