Visual information retrieval: minerva video benchmark

  • Authors:

  • Wei Ren;Paul Weal;Maneesha Singh;Sameer Singh

  • Affiliations:

  • Research School of Informatics, Loughborough University, Loughborough, UK;Research School of Informatics, Loughborough University, Loughborough, UK;Research School of Informatics, Loughborough University, Loughborough, UK;Research School of Informatics, Loughborough University, Loughborough, UK

  • Venue:
  • SPPRA'06 Proceedings of the 24th IASTED international conference on Signal processing, pattern recognition, and applications
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Content based image and video retrieval research focuses on the development of novel features and similarity metrics for improving the retrieval performance. There are only a few well-established data benchmarks on which video retrieval tools can be tested. In this paper we propose a novel benchmark for video retrieval that researchers can use in their studies for comparing features and algorithms. The benchmark comes with frame indexing for objects to assist the process of algorithm development, i.e. research can focus on higher level analysis of matching videos as opposed to spending long periods of research on low level image processing operations such as image segmentation and object definitions.