|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM342489879 |
| 003 |
DE-627 |
| 005 |
20231226014232.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2022.3183469
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1141.xml
|
| 035 |
|
|
|a (DE-627)NLM342489879
|
| 035 |
|
|
|a (NLM)35727784
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Jia, Xuemei
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Complementary Data Augmentation for Cloth-Changing Person Re-Identification
|
| 264 |
|
1 |
|c 2022
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 01.07.2022
|
| 500 |
|
|
|a Date Revised 01.07.2022
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status MEDLINE
|
| 520 |
|
|
|a This paper studies the challenging person re-identification (Re-ID) task under the cloth-changing scenario, where the same identity (ID) suffers from uncertain cloth changes. To learn cloth- and ID-invariant features, it is crucial to collect abundant training data with varying clothes, which is difficult in practice. To alleviate the reliance on rich data collection, we reinforce the feature learning process by designing powerful complementary data augmentation strategies, including positive and negative data augmentation. Specifically, the positive augmentation fulfills the ID space by randomly patching the person images with different clothes, simulating rich appearance to enhance the robustness against clothes variations. For negative augmentation, its basic idea is to randomly generate out-of-distribution synthetic samples by combining various appearance and posture factors from real samples. The designed strategies seamlessly reinforce the feature learning without additional information introduction. Extensive experiments conducted on both cloth-changing and -unchanging tasks demonstrate the superiority of our proposed method, consistently improving the accuracy over various baselines
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Zhong, Xian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ye, Mang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Wenxuan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Huang, Wenxin
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 31(2022) vom: 01., Seite 4227-4239
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:31
|g year:2022
|g day:01
|g pages:4227-4239
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2022.3183469
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 31
|j 2022
|b 01
|h 4227-4239
|