6113 search results - page 1172 / 1223 » Learning Features for Tracking |
AAAI
2010
13 years 9 months ago
2010
Lifting can greatly reduce the cost of inference on firstorder probabilistic graphical models, but constructing the lifted network can itself be quite costly. In online applicatio...
EMNLP
2007
13 years 9 months ago
2007
In Sequential Viterbi Models, such as HMMs, MEMMs, and Linear Chain CRFs, the type of patterns over output sequences that can be learned by the model depend directly on the modelâ...
AAAI
2004
13 years 9 months ago
2004
Traditionally, text classifiers are built from labeled training examples. Labeling is usually done manually by human experts (or the users), which is a labor intensive and time co...
AAAI
2006
13 years 9 months ago
2006
When humans approach the task of text categorization, they interpret the specific wording of the document in the much larger context of their background knowledge and experience. ...
DPC
1996
13 years 9 months ago
1996
Retrieving images from very large collections, using image content as a key, is becoming an important problem. Users prefer to ask for pictures using notions of content that are st...