914 search results - page 175 / 183 » Learning to Segment |
CVIU
2008
14 years 9 months ago
2008
A key problem in video content analysis using dynamic graphical models is to learn a suitable model structure given some observed visual data. We propose a Completed Likelihood AI...
CORR
1998
Springer
14 years 9 months ago
1998
Springer
Wereporthere ona studyof interannotatoragreementin the coreferencetask as defined by the MessageUnderstanding Conference(MUC-6and MUC-7).Basedon feedback from annotators, weclarif...
127
click to vote
VLSISP
2010
14 years 7 months ago
2010
Abstract In case of insufficient data samples in highdimensional classification problems, sparse scatters of samples tend to have many ‘holes’—regions that have few or no nea...
124
click to vote
KDD
2012
ACM
12 years 12 months ago
2012
ACM
Multi-instance multi-label learning (MIML) is a framework for supervised classification where the objects to be classified are bags of instances associated with multiple labels....
100
click to vote
NAACL
2003
14 years 10 months ago
2003
Searching online information is increasingly a daily activity for many people. The multilinguality of online content is also increasing (e.g. the proportion of English web users, ...