期刊
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
卷 -, 期 -, 页码 3356-3365出版社
IEEE
DOI: 10.1109/CVPR.2017.358
关键词
-
类别
资金
- NSFC [61573160, 61429201]
- ARO grant [W911NF-15-1-0290]
- NEC Laboratories of America
- Blippar
Most existing person re-identification algorithms either extract robust visual features or learn discriminative metrics for person images. However, the underlying manifold which those images reside on is rarely investigated. That raises a problem that the learned metric is not smooth with respect to the local geometry structure of the data manifold. In this paper, we study person re-identification with manifold-based affinity learning, which did not receive enough attention from this area. An unconventional manifold-preserving algorithm is proposed, which can 1) make the best use of supervision from training data, whose label information is given as pairwise constraints; 2) scale up to large repositories with low on-line time complexity; and 3) be plunged into most existing algorithms, serving as a generic postprocessing procedure to further boost the identification accuracies. Extensive experimental results on five popular person re-identification benchmarks consistently demonstrate the effectiveness of our method. Especially, on the largest CUHK03 and Market-1501, our method outperforms the state-of-the-art alternatives by a large margin with high efficiency, which is more appropriate for practical applications.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据