Semantic2Graph: graph-based multi-modal feature fusion for action segmentation in videos.

Junbin Zhang Pei-Hsuan Tsai Meng-Hsun Tsai

Published in: Appl. Intell. (2024)

Keyphrases

multi modal
feature fusion
video search
feature extraction
image segmentation
human actions
multiple features
medical images
multi modality
video sequences
video data
image analysis
action recognition
image annotation
semi supervised
image classification
data fusion
multiscale
fusion algorithm