In the real visual world, the number of categories a classifier needs to discriminate is on the order of hundreds or thousands. For example, the SUN dataset [24] contains 899 sce...
Formal analysis remains outside the mainstream of system design practice. Interactive methods and tools are regarded by some to be on the margin of useful research in this area. Al...
This paper presents novel methods for classifying images based on knowledge discovered from annotated images using WordNet. The novelty of this work is the automatic class discove...
CL Research's question-answering system (DIMAP-QA) for TREC-9 significantly extends its semantic relation triple (logical form) technology in which documents are fully parsed...
The task of learning models for many real-world problems requires incorporating domain knowledge into learning algorithms, to enable accurate learning from a realistic volume of t...
Radu Stefan Niculescu, Tom M. Mitchell, R. Bharat ...