首页> 外文会议>International conference on graphic and image processing >Cross-domain Latent Space Projection for Person Re-identification
【24h】

Cross-domain Latent Space Projection for Person Re-identification

机译:用于人员重新识别的跨域潜在空间投影

获取原文

摘要

In this paper, we research the problem of person re-identification and propose a cross-domain latent space projection (CDLSP) method to address the problems of the absence or insufficient labeled data in the target domain. Under the assumption that the visual features in the source domain and target domain share the similar geometric structure, we transform the visual features from source domain and target domain to a common latent space by optimizing the object function defined in the manifold alignment method. Moreover, the proposed object function takes into account the specific knowledge in the re-id with the aim to improve the performance of re-id under complex situations. Extensive experiments conducted on four benchmark datasets show the proposed CDLSP outperforms or is competitive with state-of-the-art methods for person re-identification.
机译:在本文中,我们研究了人员重新识别的问题,并提出了一种跨域潜在空间投影(CDLSP)方法,以解决目标域中标记数据不存在或不足的问题。在源域和目标域中的视觉特征共享相似的几何结构的假设下,我们通过优化流形对齐方法中定义的对象函数,将视觉特征从源域和目标域转换为共同的潜在空间。此外,提出的目标函数考虑了re-id中的特定知识,目的是在复杂情况下提高re-id的性能。在四个基准数据集上进行的广泛实验表明,所提出的CDLSP优于其他人,或与最新的人员识别方法相竞争。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号