Detection of Documentary Scene Changes by Audio-Visual Fusion.

Atulya Velivelli Chong-Wah Ngo Thomas S. Huang

Published in: CIVR (2003)

Keyphrases

audio visual
video scene
visual data
multi modal
person authentication
multimodal fusion
visual information
temporal context
three dimensional
moving objects
audio visual speech recognition
video summarization
video sequences
input image
image sequences
multi stream
data processing
object recognition
multiscale