Output details
11 - Computer Science and Informatics
University College London
Return to search
Output 0 of 0 in the submission
Article title
Learning a Confidence Measure for Optical Flow
Type
D - Journal article
Title of journal
IEEE Transactions on Pattern Analysis and Machine Intelligence
Article number
-
Volume number
35
Issue number
5
First page of article
1107
ISSN of journal
0162-8828
Year of publication
2012
URL
-
Number of additional authors
3
Additional information
<23>This paper established that a supervised learner can be trained to pick which of several "expert" algorithms will score highest for each variant of a problem. This is a modern and practical twist on example-based cost-sensitive learning. This and our 2010 conference paper validated this Bayesian model across three different Holy-Grail problems in Computer Vision: optical flow, descriptor matching, and patch tracking. Significance: Now being evaluated for lung-cancer screening at UCL Centre for Respiratory Research. Invited to give Rank Prize Symposium talk because this method discovers great specialist algorithms (that may be poor on average) and when to use them.
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
0
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
