Sciweavers

1584 search results - page 111 / 317
» On Combining Multiple Classifiers Using an Evidential Approa...
Sort
View
144
Voted
ECCV
2008
Springer
16 years 5 months ago
Weakly Supervised Object Localization with Stable Segmentations
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
98
Voted
ISMB
1994
15 years 4 months ago
DNA Sequence Analysis Using Hierarchical ART-based Classification Network
Adaptive resonance theory (ART)describes a class of artificial neural networkarchitectures that act as classification tools whichself-organize, workin realtime, and require no ret...
Cathie LeBlanc, Charles R. Katholi, Thomas R. Unna...
109
Voted
ICCV
2009
IEEE
15 years 1 months ago
Incremental Multiple Kernel Learning for object recognition
A good training dataset, representative of the test images expected in a given application, is critical for ensuring good performance of a visual categorization system. Obtaining ...
Aniruddha Kembhavi, Behjat Siddiquie, Roland Miezi...
CVPR
2003
IEEE
16 years 5 months ago
A Bayesian Framework for Fusing Multiple Word Knowledge Models in Videotext Recognition
Videotext recognition is challenging due to low resolution, diverse fonts/styles, and cluttered background. Past methods enhanced recognition by using multiple frame averaging, im...
DongQing Zhang, Shih-Fu Chang
ICC
2007
IEEE
149views Communications» more  ICC 2007»
15 years 9 months ago
1+N Protection Against Multiple Link Failures in Mesh Networks
Abstract—In [1], the author presented a 1+N protection strategy against single link failures using a network coding approach on p-Cycles. In this paper, we extend this approach t...
Ahmed E. Kamal