Sciweavers

387 search results - page 69 / 78
» Generative versus Discriminative Methods for Object Recognit...
Sort
View
126
Voted
CVPR
2012
IEEE
13 years 2 months ago
Unsupervised co-segmentation through region matching
Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiplescale mu...
José C. Rubio, Joan Serrat, Antonio M. L&oa...
ICB
2007
Springer
183views Biometrics» more  ICB 2007»
15 years 4 months ago
Robust Point-Based Feature Fingerprint Segmentation Algorithm
Abstract. A critical step in automatic fingerprint recognition is the accurate segmentation of fingerprint images. The objective of fingerprint segmentation is to decide which part...
Chaohong Wu, Sergey Tulyakov, Venu Govindaraju
IJCV
2008
192views more  IJCV 2008»
15 years 13 days ago
Learning to Locate Informative Features for Visual Identification
Object identification (OID) is specialized recognition where the category is known (e.g. cars) and the algorithm recognizes an object's exact identity (e.g. Bob's BMW). ...
Andras Ferencz, Erik G. Learned-Miller, Jitendra M...
ICASSP
2010
IEEE
15 years 19 days ago
The effect of lattice pruning on MMIE training
In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hy...
Long Qin, Alexander I. Rudnicky
140
Voted
AAMAS
2010
Springer
15 years 17 days ago
Teaching a pet-robot to understand user feedback through interactive virtual training tasks
Abstract In this paper, we present a human-robot teaching framework that uses "virtual" games as a means for adapting a robot to its user through natural interaction in a...
Anja Austermann, Seiji Yamada