Name
Title | ||
|---|---|---|
Person re-identification with fusion of hand-crafted and deep pose-based body region features. |
Abstract | ||
|---|---|---|
Person re-identification (re-ID) aims to accurately re- trieve a person from a large-scale database of images cap- tured across multiple cameras. Existing works learn deep representations using a large training subset of unique per- sons. However, identifying unseen persons is critical for a good re-ID algorithm. Moreover, the misalignment be- tween person crops to detection errors or pose variations leads to poor feature matching. In this work, we present a fusion of handcrafted features and deep feature representa- tion learned using multiple body parts to complement the global body features that achieves high performance on un- seen test images. Pose information is used to detect body regions that are passed through Convolutional Neural Net- works (CNN) to guide feature learning. Finally, a metric learning step enables robust distance matching on a dis- criminative subspace. Experimental results on 4 popular re-ID benchmark datasets namely VIPer, DukeMTMC-reID, Market-1501 and CUHK03 show that the proposed method achieves state-of-the-art performance in image-based per- son re-identification. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Computer Vision and Pattern Recognition | Subspace topology,Pattern recognition,Computer science,Fusion,Feature matching,Artificial intelligence,Artificial neural network,Feature learning |
DocType | Volume | Citations |
Journal | abs/1803.10630 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jubin Johnson | 1 | 26 | 3.82 |
| Shunsuke Yasugi | 2 | 0 | 0.34 |
| Yoichi Sugino | 3 | 0 | 0.34 |
| Sugiri Pranata | 4 | 36 | 5.78 |
| Sheng Mei Shen | 5 | 131 | 13.13 |