Spatial As Deep: Spatial CNN for Traffic Scene Understanding

national conference on artificial intelligence, 2018.

Cited by: 139|Bibtex|Views94|Links
EI

Abstract:

Convolutional neural networks (CNNs) are usually built by stacking convolutional operations layer-by-layer. Although CNN has shown strong capability to extract semantics from raw pixels, its capacity to capture spatial relationships of pixels across rows and columns of an image is not fully explored. These relationships are important to l...More

Code:

Data:

Your rating :
0

 

Tags
Comments