从一瞥到“抓到你”：基于渐进相关反馈的交互式人脸图像检索
From A Glance to "Gotcha": Interactive Facial Image Retrieval with Progressive Relevance Feedback
摘要：
面部图像检索在法医调查中起着重要的作用，其中未经训练的证人试图从大量的图像中识别嫌疑人。然而，由于难以口头和直接地描述人类面部外观，人们自然倾向于通过参考众所周知的现有图像并将面部的特定区域与它们进行比较来描绘，并且每次提供完整的比较也是具有挑战性的。因此，我们提出了一个端到端的框架来检索面部图像与相关反馈逐步提供的证人，使历史信息在多个回合的开发和交互式和迭代的方法来检索的心理形象。由于不需要任何额外的注释，我们的模型可以以一点响应工作为代价来应用。在\texttt{CelebA}上进行了实验，通过百分位数排序来评估性能，在最佳设置下，性能达到99%.由于这一主题仍然很少探索到我们所知道的最好的，我们希望我们的工作可以作为一个垫脚石，为进一步的研究。
英文摘要：
Facial image retrieval plays a significant role in forensic investigations where an untrained witness tries to identify a suspect from a massive pool of images. However, due to the difficulties in describing human facial appearances verbally and directly, people naturally tend to depict by referring to well-known existing images and comparing specific areas of faces with them and it is also challenging to provide complete comparison at each time. Therefore, we propose an end-to-end framework to retrieve facial images with relevance feedback progressively provided by the witness, enabling an exploitation of history information during multiple rounds and an interactive and iterative approach to retrieving the mental image. With no need of any extra annotations, our model can be applied at the cost of a little response effort. We experiment on \texttt{CelebA} and evaluate the performance by ranking percentile and achieve 99\% under the best setting. Since this topic remains little explored to the best of our knowledge, we hope our work can serve as a stepping stone for further research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
