Abstract | ||
---|---|---|
•We are the first to model human silhouette extraction and gait recognition in one framework in a unified end-to-end learning manner.•We find that joint learning can lead to obvious performance enhancement over separate learning.•We explore to add siamese loss for metric learning across the segmentation network and recognition network.•We build a new outdoor gait database containing three challenging scenes.•We provide extensive empirical evaluations in experiments and obtain the state-of-the-art results on three gait recognition datasets. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.patcog.2019.106988 | Pattern Recognition |
Keywords | Field | DocType |
Gait recognition,Video-based human identification,End-to-end CNN,Joint learning | Pattern recognition,Gait,Convolutional neural network,Silhouette,Segmentation,Feature extraction,Artificial intelligence,Independence (probability theory),Mathematics,Feature learning,Performance improvement | Journal |
Volume | Issue | ISSN |
96 | 1 | 0031-3203 |
Citations | PageRank | References |
3 | 0.42 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chunfeng Song | 1 | 54 | 8.53 |
Yongzhen Huang | 2 | 9 | 1.53 |
Yan Huang | 3 | 226 | 27.65 |
Ning Jia | 4 | 5 | 0.81 |
Liang Wang | 5 | 128 | 12.87 |