Semantic-Guided Multi-feature Fusion for Accurate Video Captioning.

Yunjie Zhang Tianyang Xu Xiaoning Song Zhenghua Feng Xiaojun Wu

Published in: ICIG (4) (2023)

Keyphrases

feature fusion
video sequences
video data
multiple features
feature extraction
video frames
high level
fusion algorithm
image processing
data analysis
semantic information
single feature