Instance search retrospective with focus on TRECVID

  • George Awad
  • Wessel Kraaij
  • Paul Over
  • Shin’ichi Satoh
Trends and Surveys

DOI: 10.1007/s13735-017-0121-3

Cite this article as:
Awad, G., Kraaij, W., Over, P. et al. Int J Multimed Info Retr (2017) 6: 1. doi:10.1007/s13735-017-0121-3
  • 91 Downloads

Abstract

This paper presents an overview of the Video instance search benchmark which was run over a period of 6 years (2010–2015) as part of the TREC Video Retrieval workshop series. The main contributions of the paper include (i) an examination of the evolving design of the evaluation framework and its components (system tasks, data, measures); (ii) an analysis of the influence of topic characteristics (such as rigid/non-rigid, planar/non-planar, stationary/mobile on performance; (iii) a high-level overview of results and best-performing approaches. The instance search benchmark worked with a variety of large collections of data including Sound & Vision, Flickr, BBC Rushes for the first three pilot years and with the small world of the BBC EastEnders series for the last 3 years.

Keywords

Instance search Multimedia Evaluation TRECVID 

Copyright information

© Springer-Verlag London (outside the USA) 2017

Authors and Affiliations

  1. 1.Dakota Consulting, Inc.Silver SpringUSA
  2. 2.National Institute of Standards and TechnologyGaithersburgUSA
  3. 3.TNOThe HagueThe Netherlands
  4. 4.Leiden UniversityLeidenThe Netherlands
  5. 5.National Institute of InformaticsTokyoJapan

Personalised recommendations