Look longer to see better: Audio-visual event localization by exploiting long-term correlation.

Longyin Guo Qijun Zhao Hongmei Gao

Published in: IJCNN (2022)

Keyphrases

audio visual
long term
multi modal
visual information
visual data
multimedia
multi stream
emotion recognition
event detection
video summarization
temporal context
audio visual speech recognition
person authentication
data sources
human computer interaction
sound source