Human performance measures for video retrieval

  • Authors:
  • Gary Marchionini

  • Affiliations:
  • University of North Carolina, Chapel Hill, NC

  • Venue:
  • MIR '06 Proceedings of the 8th ACM international workshop on Multimedia information retrieval
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we describe the challenges of assessing human performance during video retrieval episodes and describe several measures of human performance that have been used in developing visual surrogates for the Open Video Digital Library (http://www.open-video.org). These include two sets of cognitive performance measures that aim to assess human recognition and inference and a set of attitudinal measures that aim to assess user satisfaction with video surrogates.