Stepwise Fusion Transformer for Affective Video Content Analysis.

Zeyu Chen Xiaohong Xiang Xin Deng Qi Wang

Published in: NCAA (2) (2023)

Keyphrases

video content analysis
content analysis
video analysis
sports video
surveillance videos
spatial context
data fusion
shot boundary detection
human computer interaction
multi sensor
multiple features
semantic analysis
natural language
event detection
video data
multi modal
collaborative learning
learning process