Title
Geodesic propagation for semantic labeling.
Abstract
This paper presents a semantic labeling framework with geodesic propagation (GP). Under the same framework, three algorithms are proposed, including GP, supervised GP (SGP) for image, and hybrid GP (HGP) for video. In these algorithms, we resort to the recognition proposal map and select confident pixels with maximum probability as the initial propagation seeds. From these seeds, the GP algorithm ...
Year
DOI
Venue
2014
10.1109/TIP.2014.2358193
IEEE Transactions on Image Processing
Keywords
Field
DocType
Labeling,Semantics,Algorithm design and analysis,Image color analysis,Image edge detection,Image segmentation
Computer vision,Pattern recognition,Image texture,Binary image,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Connected-component labeling,Minimum spanning tree-based segmentation,Geodesic,Mathematics,Computational complexity theory
Journal
Volume
Issue
ISSN
23
11
1057-7149
Citations 
PageRank 
References 
7
0.44
49
Authors
6
Name
Order
Citations
PageRank
qing li1202.00
Xiaowu Chen260545.05
Yafei Song3365.63
Yu Zhang4367.56
Xin Jin516217.20
Qinping Zhao636343.20