Many human action recognition tasks involve data that can be factorized into multiple views such as body postures and hand shapes. These views often interact with each other over ...
Programming with dependent types is a blessing and a curse. It is a blessing to be able to bake invariants into the definition of datatypes: we can finally write correct-by-cons...
Current modularity-based community detection methods show decreased performance as relational networks become increasingly noisy. These methods also yield a large number of divers...
Facial activities are the most natural and powerful means of human communication. Spontaneous facial activity is characterized by rigid head movements, non-rigid facial muscular m...
Knowledge-sharing communities like Wikipedia and automated extraction methods like those of DBpedia enable the construction of large machine-processible knowledge bases with relat...