421 search results - page 13 / 85 » Reducing Label Complexity by Learning From Bags |
CVPR
2005
IEEE
15 years 11 months ago
2005
IEEE
Training datasets for learning of object categories are often contaminated or imperfect. We explore an approach to automatically identify examples that are noisy or troublesome fo...
83
Voted
ICCV
2009
IEEE
16 years 2 months ago
2009
IEEE
In this paper, we investigate the detection of semantic
human actions in complex scenes. Unlike conventional
action recognition in well-controlled environments,
action detection...
KDD
2006
ACM
15 years 10 months ago
2006
ACM
Many applications in text processing require significant human effort for either labeling large document collections (when learning statistical models) or extrapolating rules from...
90
Voted
ECAI
2010
Springer
14 years 10 months ago
2010
Springer
Abstract. Learning event models from videos has applications ranging from abnormal event detection to content based video retrieval. Relational learning techniques such as Inductiv...
NIPS
2008
14 years 11 months ago
2008
We apply robust Bayesian decision theory to improve both generative and discriminative learners under bias in class proportions in labeled training data, when the true class propo...