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

Uma Srinivasan Craig A. Lindley

Published in: VISUAL (1999)

Keyphrases

multi modal
feature maps
video sequences
multi modality
kernel function
self organizing maps
cross modal
video data
humanoid robot
video frames
training samples
high dimensional
image sequences
video content
image classification
facial expressions
multiscale