• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Distance Metric Learning Using Privileged Information for Face Verification and Person Re-Identification
【24h】

Distance Metric Learning Using Privileged Information for Face Verification and Person Re-Identification

机译：使用特权信息进行面部验证和人员重新识别的远程度量学习

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we propose a new approach to improve face verification and person re-identification in the RGB images by leveraging a set of RGB-D data, in which we have additional depth images in the training data captured using depth cameras such as Kinect. In particular, we extract visual features and depth features from the RGB images and depth images, respectively. As the depth features are available only in the training data, we treat the depth features as privileged information, and we formulate this task as a distance metric learning with privileged information problem. Unlike the traditional face verification and person re-identification tasks that only use visual features, we further employ the extra depth features in the training data to improve the learning of distance metric in the training process. Based on the information-theoretic metric learning (ITML) method, we propose a new formulation called ITML with privileged information (ITML+) for this task. We also present an efficient algorithm based on the cyclic projection method for solving the proposed ITML+ formulation. Extensive experiments on the challenging faces data sets EUROCOM and CurtinFaces for face verification as well as the BIWI RGBD-ID data set for person re-identification demonstrate the effectiveness of our proposed approach.
机译：在本文中，我们提出了一种通过利用一组RGB-D数据来改善RGB图像中的人脸验证和人物重新识别的新方法，其中在使用Kinect等深度相机捕获的训练数据中，我们还有其他深度图像。特别是，我们分别从RGB图像和深度图像中提取视觉特征和深度特征。由于深度特征仅在训练数据中可用，因此我们将深度特征视为特权信息，并将此任务表述为具有特权信息问题的距离度量学习。与仅使用视觉特征的传统人脸验证和人员重新识别任务不同，我们在训练数据中进一步采用了额外的深度特征，以改善训练过程中距离度量的学习。基于信息理论度量学习（ITML）方法，我们针对此任务提出了一种新的公式，称为具有特权信息的ITML（ITML +）。我们还提出了一种基于循环投影方法的有效算法，用于解决提出的ITML +公式。在具有挑战性的人脸数据集EUROCOM和CurtinFaces进行人脸验证以及BIWI RGBD-ID数据集以进行人员重新识别方面的大量实验证明了我们提出的方法的有效性。

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