Supervised learning methods for diversification of image search results

Goynuk B., Altingövde I. S.

42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, 14 - 17 April 2020, pp.158-165 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1007/978-3-030-45442-5_20
  • City: Lisbon
  • Country: Portugal
  • Page Numbers: pp.158-165
  • Middle East Technical University Affiliated: Yes

Abstract

© Springer Nature Switzerland AG 2020.We adopt a supervised learning framework, namely R-LTR [17], to diversify image search results, and extend it in various ways. Our experiments show that the adopted and proposed variants are superior to two well-known baselines, with relative gains up to 11.4%.