mirrors
/
person-re-ranking
mirror of https://github.com/zhunzhong07/person-re-ranking
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Update README.md

pull/25/head
zhun zhong 2017-05-05 13:06:18 +08:00 committed by GitHub
parent d5c2e54e43
commit 7a1c724ecf
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@ -35,7 +35,7 @@ The new training/testing protocol split for CUHK03 in our paper is in the "evalu
- cuhk03_new_protocol_config_labeled.mat - cuhk03_new_protocol_config_labeled.mat
================================================================ ================================================================
## IDE Baseline ## IDE Baseline + Re-ranking
### Requirements: Caffe ### Requirements: Caffe
@ -119,7 +119,7 @@ For Market-1501, these results are better than those reported in our paper, sinc
| | Labeled | Labeled| detected | detected| | | Labeled | Labeled| detected | detected|
| -------| ----- | ---- |---- |---- | | -------| ----- | ---- |---- |---- |
|Methods | Rank@1 | mAP| Rank@1 | mAP| |Methods | Rank@1 | mAP| Rank@1 | mAP|
|LOMO + XQDA | 14.8% | 13.6%|12.8% | 11.5%| |LOMO + XQDA [1] | 14.8% | 13.6%|12.8% | 11.5%|
|LOMO + XQDA + re-ranking | 19.1% | 20.8%|16.6% | 17.8%| |LOMO + XQDA + re-ranking | 19.1% | 20.8%|16.6% | 17.8%|
|IDE_CaffeNet + Euclidean | 15.6% | 14.9%| 15.1% | 14.2%| |IDE_CaffeNet + Euclidean | 15.6% | 14.9%| 15.1% | 14.2%|
|IDE_CaffeNet + Euclidean + re-ranking | 19.1% | 21.3%|19.3% | 20.6%| |IDE_CaffeNet + Euclidean + re-ranking | 19.1% | 21.3%|19.3% | 20.6%|
@ -130,6 +130,11 @@ For Market-1501, these results are better than those reported in our paper, sinc
|IDE_ResNet_50 + XQDA | 32.0% | 29.6%|31.1% | 28.2%| |IDE_ResNet_50 + XQDA | 32.0% | 29.6%|31.1% | 28.2%|
|IDE_ResNet_50 + XQDA + re-ranking | 38.1% | 40.3%|34.7% | 37.4%| |IDE_ResNet_50 + XQDA + re-ranking | 38.1% | 40.3%|34.7% | 37.4%|
### References
[1] Person re-identification by local maximal occurrence representation and metric learning. Liao S, Hu Y, Zhu X, et al. In CVPR. 2015
[2] Sparse contextual activation for efficient visual re-ranking. Bai, Song and Bai, Xiang. IEEE Transactions on Image Processing. 2016
### Contact us ### Contact us
If you have any questions about this code, please do not hesitate to contact us. If you have any questions about this code, please do not hesitate to contact us.