Face retrieval framework relying on user's visual memory

Yugo Sato, Tsukasa Fukusato, Shigeo Morishima

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper presents an interactive face retrieval framework for clarifying an image representation envisioned by a user. Our system is designed for a situation in which the user wishes to find a person but has only visual memory of the person. We address a critical challenge of image retrieval across the user's inputs. Instead of target-specific information, the user can select several images (or a single image) that are similar to an impression of the target person the user wishes to search for. Based on the user's selection, our proposed system automatically updates a deep convolutional neural network. By interactively repeating these process (human-in-the-loop optimization), the system can reduce the gap between human-based similarities and computer-based similarities and estimate the target image representation. We ran user studies with 10 subjects on a public database and confirmed that the proposed framework is effective for clarifying the image representation envisioned by the user easily and quickly.

Original languageEnglish
Title of host publicationICMR 2018 - Proceedings of the 2018 ACM International Conference on Multimedia Retrieval
PublisherAssociation for Computing Machinery, Inc
Pages274-282
Number of pages9
ISBN (Print)9781450350464
DOIs
Publication statusPublished - 2018 Jun 5
Event8th ACM International Conference on Multimedia Retrieval, ICMR 2018 - Yokohama, Japan
Duration: 2018 Jun 112018 Jun 14

Other

Other8th ACM International Conference on Multimedia Retrieval, ICMR 2018
CountryJapan
CityYokohama
Period18/6/1118/6/14

Keywords

  • Active learning
  • Deep convolutional neural network
  • Relevance feedback
  • User interaction

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Face retrieval framework relying on user's visual memory'. Together they form a unique fingerprint.

  • Cite this

    Sato, Y., Fukusato, T., & Morishima, S. (2018). Face retrieval framework relying on user's visual memory. In ICMR 2018 - Proceedings of the 2018 ACM International Conference on Multimedia Retrieval (pp. 274-282). Association for Computing Machinery, Inc. https://doi.org/10.1145/3206025.3206038