Cross-modal attention fusion network for RGB-D semantic segmentation.

Qiankun Zhao Yingcai Wan Jiqian Xu Lijin Fang

Published in: Neurocomputing (2023)

Keyphrases

cross modal
semantic segmentation
multi modal
conditional random fields
superpixels
weakly supervised
pairwise
image retrieval
multimedia
object detection
visual attention
object categories
object classes
scene classification