SATNet combines a decoupled attention module and dual texture/saliency pyramids for RGB-D salient object detection, reporting strong benchmark accuracy while omitting the depth-estimation model from its efficiency accounting.
Non- rigid object tracking via deep multi-scale spatial-temporal discriminative saliency maps,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff Perspective
SATNet combines a decoupled attention module and dual texture/saliency pyramids for RGB-D salient object detection, reporting strong benchmark accuracy while omitting the depth-estimation model from its efficiency accounting.