Sciweavers

313 search results - page 25 / 63
» Estimating labels from label proportions
Sort
View
ICPR
2010
IEEE
15 years 9 months ago
Pattern Recognition Using Functions of Multiple Instances
The Functions of Multiple Instances (FUMI) method for learning a target prototype from data points that are functions of target and non-target prototypes is introduced. In this pa...
Alina Zare, Paul Gader
ICASSP
2008
IEEE
16 years 16 days ago
Confidence scores for acoustic model adaptation
This paper focuses on confidence scores for use in acoustic model adaptation. Frame-based confidence estimates are used in linear transform (CMLLR and MLLR) and MAP adaptation. ...
Christian Gollan, Michiel Bacchiani
ECCV
1994
Springer
15 years 10 months ago
Markov Random Field Models in Computer Vision
A variety of computer vision problems can be optimally posed as Bayesian labeling in which the solution of a problem is dened as the maximum a posteriori (MAP) probability estimate...
Stan Z. Li
LREC
2008
78views Education» more  LREC 2008»
15 years 7 months ago
Approximating Learning Curves for Active-Learning-Driven Annotation
Active learning (AL) is getting more and more popular as a methodology to considerably reduce the annotation effort when building training material for statistical learning method...
Katrin Tomanek, Udo Hahn
CVPR
2012
IEEE
13 years 8 months ago
Discovering discriminative action parts from mid-level video representations
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
Michalis Raptis, Iasonas Kokkinos, Stefano Soatto