Login / Signup
DAGNet: Depth-aware Glass-like objects segmentation via cross-modal attention.
Yingcai Wan
Qiankun Zhao
Jiqian Xu
Huaizhen Wang
Lijin Fang
Published in:
J. Vis. Commun. Image Represent. (2024)
Keyphrases
</>
cross modal
perceptual information
multi modal
visual data
image regions
image segmentation
bounding box
visual recognition
d objects
visual similarity
multiscale
image retrieval
visual attention
multimedia databases
object classes