Login / Signup
DXNet: An Encoder-Decoder Architecture with XSPP for Semantic Image Segmentation in Street Scenes.
Yexin Shang
Shan Zhong
Shengrong Gong
Lifan Zhou
Wenhao Ying
Published in:
ICONIP (5) (2019)
Keyphrases
</>
street scenes
image segmentation
video codec
semantic segmentation
decoding process
distributed video coding
markov random field
motion estimation
multiscale
graph cuts
level set
rate distortion
depth estimation
bit rate
wyner ziv
image quality
deformable models
expectation maximization