A Convolutional Encoder-Decoder Network With Skip Connections for Saliency Prediction

In this paper, we propose a novel convolutional encoder-decoder network with skip connections, named CEDNS, to improve the performance of saliency prediction. The encoder network utilizes the DenseNet model as the stem network to extract abundant hierarchical features from input images. Subsequently...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Fei Qi, Chunhuan Lin, Guangming Shi, Hao Li
Format:	Artigo
Sprog:	Inglês
Udgivet:	IEEE 2019-01-01
Serier:	IEEE Access
Fag:	Saliency convolutional neural networks encoder-decoder skip connections visual attention
Online adgang:	https://ieeexplore.ieee.org/document/8709735/
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!