UCTNet: Uncertainty-Aware Cross-Modal Transformer Network for Indoor RGB-D Semantic Segmentation.

Xiaowen Ying Mooi Choo Chuah

Published in: ECCV (30) (2022)

Keyphrases

cross modal
semantic segmentation
multi modal
superpixels
computer vision
conditional random fields
object categories
machine learning
image sequences
human body
object segmentation
weakly supervised