3DSEAVNet: 3D-Squeeze-and-Excitation Networks for Audio-Visual Saliency Prediction.

Silong Liang Chunxiao Li Naying Cui Minghui Sun Hao Xue

Published in: IJCNN (2023)

Keyphrases

visual saliency
saliency map
visual attention
natural images
multimedia
visual saliency detection
saliency model
natural scenes
human detection
eye movements
prediction error
focus of attention
real time
visual information
bayesian framework
video sequences
high quality