• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Biometric and surveillance technology for human and activity identification X >How Reliable are Your Visual Attributes?
【24h】

How Reliable are Your Visual Attributes?

机译：视觉属性的可靠性如何？

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

Describable visual attributes are a powerful way to label aspects of an image, and taken together, build a detailed representation of a scene's appearance. Attributes enable highly accurate approaches to a variety of tasks, including object recognition, face recognition and image retrieval. An important consideration not previously addressed in the literature is the reliability of attribute classifiers as the quality of an image degrades. In this paper, we introduce a general framework for conducting reliability studies that assesses attribute classifier accuracy as a function of image degradation. This framework allows us to bound, in a probabilistic manner, the input imagery that is deemed acceptable for consideration by the attribute system - without requiring ground truth attribute labels. We introduce a novel differential probabilistic model for accuracy assessment that leverages a strong normalization procedure based on the statistical extreme value theory. To demonstrate the utility of our framework, we present an extensive case study using 64 unique facial attributes, computed on data derived from the Labeled Faces in the Wild (LFW) data set. We also show that such reliability studies can result in significant compression benefits for mobile applications.
机译：可描述的视觉属性是标记图像各方面的强大方法，并且结合起来可以构建场景外观的详细表示。通过属性，可以高度精确地执行各种任务，包括对象识别，面部识别和图像检索。先前文献中未解决的重要考虑因素是属性分类器的可靠性，因为图像质量会下降。在本文中，我们介绍了一个进行可靠性研究的通用框架，该框架评估属性分类器的准确度与图像退化的关系。该框架允许我们以概率方式绑定属性系统认为可以接受的输入图像-不需要地面真实属性标签。我们介绍了一种新的用于概率评估的差分概率模型，该模型利用了基于统计极值理论的强大归一化过程。为了演示我们框架的实用性，我们使用64种独特的面部属性进行了广泛的案例研究，这些属性是根据从“野外标记的面部”（LFW）数据集得出的数据计算得出的。我们还表明，这种可靠性研究可以为移动应用程序带来显着的压缩优势。

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