Title |
End-to-End Comparative Attention Networks for Person Re-Identification
|
---|---|
Published in |
IEEE Transactions on Image Processing, May 2017
|
DOI | 10.1109/tip.2017.2700762 |
Pubmed ID | |
Authors |
Hao Liu, Jiashi Feng, Meibin Qi, Jianguo Jiang, Shuicheng Yan |
Abstract |
Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies in the lack of spatial and temporal cues, which makes it difficult to deal with large variations of lighting conditions, viewing angles, body poses and occlusions. Recently, several deep learning based person re-identification approaches have been proposed and achieved remarkable performance. However, most of those approaches extract discriminative features from the whole frame at one glimpse without differentiating various parts of the persons to identify. It is essentially important to examine multiple highly discriminative local regions of the person images in details through multiple glimpses for dealing with the large appearance variance. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
India | 1 | 33% |
Unknown | 2 | 67% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 2 | 67% |
Scientists | 1 | 33% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
China | 1 | <1% |
Singapore | 1 | <1% |
Unknown | 261 | 99% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 62 | 24% |
Student > Master | 56 | 21% |
Researcher | 17 | 6% |
Student > Postgraduate | 12 | 5% |
Student > Bachelor | 10 | 4% |
Other | 29 | 11% |
Unknown | 77 | 29% |
Readers by discipline | Count | As % |
---|---|---|
Computer Science | 145 | 55% |
Engineering | 23 | 9% |
Economics, Econometrics and Finance | 3 | 1% |
Mathematics | 2 | <1% |
Earth and Planetary Sciences | 2 | <1% |
Other | 5 | 2% |
Unknown | 83 | 32% |