Visual saliency detection via a recurrent residual convolutional neural network based on densely aggregated features

Current visual saliency detection algorithms based on deep learning suffer from reduced detection effect in complex scenes owing to ineffective feature expression and poor generalization. The present study addresses this issue by proposing a recurrent residual network based on dense aggregated featu...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computers & graphics 2022-05, Vol.104, p.72-85
Hauptverfasser:	Hua, Chunjian, Zou, Xintong, Ling, Yan, Chen, Ying
Format:	Artikel
Sprache:	eng
Schlagworte:	Agglomeration Algorithms Artificial neural networks Dense aggregated features Feature extraction Image segmentation Machine learning Optimization Recurrent residual network Salience Visual saliency detection
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!