Sciweavers

1746 search results - page 212 / 350
» Hierarchical Unsupervised Learning
Sort
View
CVPR
2004
IEEE
16 years 6 months ago
Is Bottom-Up Attention Useful for Object Recognition?
A key problem in learning multiple objects from unlabeled images is that it is a priori impossible to tell which part of the image corresponds to each individual object, and which...
Ueli Rutishauser, Dirk Walther, Christof Koch, Pie...
CVPR
2006
IEEE
16 years 6 months ago
Automatic Discovery of Action Taxonomies from Multiple Views
We present a new method for segmenting actions into primitives and classifying them into a hierarchy of action classes. Our scheme learns action classes in an unsupervised manner ...
Daniel Weinland, Rémi Ronfard, Edmond Boyer
ICPR
2008
IEEE
16 years 5 months ago
Audio-visual event classification via spatial-temporal-audio words
In this paper, we propose a generative model-based approach for audio-visual event classification. This approach is based on a new unsupervised learning method using an extended p...
Ming Li, Sanqing Hu, Shih-Hsi Liu, Sung Baang, Yu ...
ICML
2009
IEEE
16 years 5 months ago
Multi-class image segmentation using conditional random fields and global classification
A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentatio...
Nils Plath, Marc Toussaint, Shinichi Nakajima
ICML
2005
IEEE
16 years 5 months ago
Analysis and extension of spectral methods for nonlinear dimensionality reduction
Many unsupervised algorithms for nonlinear dimensionality reduction, such as locally linear embedding (LLE) and Laplacian eigenmaps, are derived from the spectral decompositions o...
Fei Sha, Lawrence K. Saul