Title
Exploring Weakly Labeled Images for Video Object Segmentation With Submodular Proposal Selection.
Abstract
Video object segmentation (VOS) is important for various computer vision problems, and handling it with minimal human supervision is highly desired for the large-scale applications. To bring down the supervision, existing approaches largely follow a data mining perspective by assuming the availability of multiple videos sharing the same object categories. It, however, would be problematic for the ...
Year
DOI
Venue
2018
10.1109/TIP.2018.2806995
IEEE Transactions on Image Processing
Keywords
Field
DocType
Proposals,Object segmentation,Training,Image segmentation,Noise measurement,Manuals,Detectors
Noise measurement,Voting,Pattern recognition,Segmentation,Submodular set function,Image segmentation,Artificial intelligence,Spatial contextual awareness,Mathematics
Journal
Volume
Issue
ISSN
27
9
1057-7149
Citations 
PageRank 
References 
1
0.35
36
Authors
5
Name
Order
Citations
PageRank
Yu Zhang1367.56
Xiaowu Chen260545.05
Jia Li352442.09
teng, w.4163.70
Haokun Song510.35