Three-Stream Attention-Aware Network for RGB-D Salient Object Detection

Previous RGB-D fusion systems based on convolutional neural networks typically employ a two-stream architecture, in which RGB and depth inputs are learned independently. The multi-modal fusion stage is typically performed by concatenating the deep features from each stream in the inference process....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing 2019-06, Vol.28 (6), p.2825-2835
Hauptverfasser:	Chen, Hao, Li, Youfu
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Cognition Computer architecture Convolutional neural networks cross-modal cross-level attention Distillation Feature extraction Feature maps Object detection Object recognition RGB-D Salience Saliency detection Three-stream
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!