Sciweavers

324 search results - page 20 / 65
» Attention can improve a simple model for object recognition
Sort
View
71
Voted
TSMC
2010
14 years 4 months ago
Toward Unconstrained Ear Recognition From Two-Dimensional Images
Abstract--Ear recognition, as a biometric, has several advantages. In particular, ears can be measured remotely and are also relatively static in size and structure for each indivi...
John D. Bustard, Mark S. Nixon
ICCV
2005
IEEE
15 years 11 months ago
Efficient Learning of Relational Object Class Models
We present an efficient method for learning part-based object class models from unsegmented images represented as sets of salient features. A model includes parts' appearance...
Aharon Bar-Hillel, Tomer Hertz, Daphna Weinshall
69
Voted
ICCV
2005
IEEE
15 years 3 months ago
Learning Models for Predicting Recognition Performance
This paper addresses one of the fundamental problems encountered in performance prediction for object recognition. In particular we address the problems related to estimation of s...
Rong Wang, Bir Bhanu
CVPR
2008
IEEE
15 years 11 months ago
Margin-based discriminant dimensionality reduction for visual recognition
Nearest neighbour classifiers and related kernel methods often perform poorly in high dimensional problems because it is infeasible to include enough training samples to cover the...
Hakan Cevikalp, Bill Triggs, Frédéri...
TASLP
2008
105views more  TASLP 2008»
14 years 9 months ago
Optimizing the Performance of Spoken Language Recognition With Discriminative Training
The performance of spoken language recognition system is typically formulated to reflect the detection cost and the strategic decision points along the detection-error-tradeoff cur...
Donglai Zhu, Haizhou Li, Bin Ma, Chin-Hui Lee