Video semantic segmentation via feature propagation with holistic attention.

Junrong Wu Zongzheng Wen Sanyuan Zhao Kele Huang

Published in: Pattern Recognit. (2020)

Keyphrases

semantic segmentation
label transfer
conditional random fields
superpixels
video data
weakly supervised
video sequences
video frames
feature vectors
scene classification
visual attention
object class
image set
pascal voc
object categories
bag of words
viewpoint
long range
computer vision
multiscale