Multi-modal Feature-map: An Approach to Represent Digital Video Sequences

  • Authors:
  • Uma Srinivasan;Craig A. Lindley

  • Affiliations:
  • -;-

  • Venue:
  • VISUAL '99 Proceedings of the Third International Conference on Visual Information and Information Systems
  • Year:
  • 1999

Quantified Score

Hi-index 0.01

Visualization

Abstract

Video sequences retrieved from a database need to be presented in a compact, meaningful way in order to enable users to understand and visualise the contents presented. In this paper we propose a visual representation that exploits the multi-modal content of video sequences by representing retrieved video sequences with a set of multi-modal feature-maps arranged in a temporal order. The feature-map is a collage represented as a visual icon that shows: the perceptual content such as a key-frame image, the cinematic content such as the type of camera work, some auditory content that represents the type of auditory information present in the sequence, temporal information that shows the duration of the sequence and its offset within the video.