首页> 外文会议>International conference on graphic and image processing >Deep Classification Hashing for Person Re-Identification
【24h】

Deep Classification Hashing for Person Re-Identification

机译:用于人员重新识别的深度分类哈希

获取原文

摘要

As the development of surveillance in public, person re-identification becomes more and more important. The large-scale databases call for efficient computation and storage, hashing technique is one of the most important methods. In this paper, we proposed a new deep classification hashing network by introducing a new binary appropriation layer in the traditional imageNet pre-trained CNN models. It outputs binary appropriate features, which can be easily quantized into binary hash-codes for hamming similarity comparison. Experiments show that our deep hashing method can outperform the state-of-the-art methods on the public CUHK03 and Marketl501 datasets.
机译:随着公共监视的发展,人们的重新识别越来越重要。大规模数据库要求有效的计算和存储,哈希技术是最重要的方法之一。在本文中,我们通过在传统的imageNet预训练的CNN模型中引入新的二进制专用层,提出了一种新的深度分类哈希网络。它输出适当的二进制特征,可以很容易地将其量化为二进制哈希码,以进行汉明相似度比较。实验表明,在公共CUHK03和Marketl501数据集上,我们的深度哈希方法优于最新方法。

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