227 search results - page 39 / 46 » Learning to Localize Objects with Structured Output Regressi... |
CVPR
2008
IEEE
15 years 11 months ago
2008
IEEE
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
ICDAR
2007
IEEE
15 years 3 months ago
2007
IEEE
The Machine Learning and Pattern Recognition communities are facing two challenges: solving the normalization problem, and solving the deep learning problem. The normalization pro...
JMLR
2010
14 years 4 months ago
2010
Deep belief nets have been successful in modeling handwritten characters, but it has proved more difficult to apply them to real images. The problem lies in the restricted Boltzma...
ICML
2010
IEEE
14 years 10 months ago
2010
IEEE
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...
KDD
2007
ACM
15 years 10 months ago
2007
ACM
In analyzing data from social and communication networks, we encounter the problem of classifying objects where there is an explicit link structure amongst the objects. We study t...