6113 search results - page 755 / 1223 » Learning Features for Tracking |
144
click to vote
ACL
2010
15 years 4 months ago
2010
We show that using confidence-weighted classification in transition-based parsing gives results comparable to using SVMs with faster training and parsing time. We also compare wit...
198
click to vote
SIAMJO
2010
15 years 1 months ago
2010
We study the problem of minimizing the expected loss of a linear predictor while constraining its sparsity, i.e., bounding the number of features used by the predictor. While the r...
191
Voted
CVPR
2005
IEEE
16 years 9 months ago
2005
IEEE
Dimensionality reduction via feature projection has been widely used in pattern recognition and machine learning. It is often beneficial to derive the projections not only based o...
174
Voted
CVPR
2008
IEEE
16 years 9 months ago
2008
IEEE
We propose an approach for learning visual models of object categories in an unsupervised manner in which we first build a large-scale complex network which captures the interacti...
212
click to vote
ECCV
2008
Springer
16 years 8 months ago
2008
Springer
We present a learning-based, sliding window-style approach for the problem of detecting humans in still images. Instead of traditional concatenation-style image location-based feat...