FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition

FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition

Scene recognition is a kind of image recognition problems which is aimed at predicting the category of the place at which the image is taken. In this paper, a new scene recognition method using the convolutional neural network (CNN) is proposed. The proposed method is based on the fusion of the obje...

Full description

Bibliographic Details
Main Authors: Hongje Seong, Junhyuk Hyun, Euntai Kim
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Scene recognition
convolutional neural network
fusion network
scene coherence
end-to-end trainable
Online Access:https://ieeexplore.ieee.org/document/9076601/

Internet

https://ieeexplore.ieee.org/document/9076601/

Similar Items