Semi-supervised understanding of complex activities from temporal concepts
AVSS, pp. 80-87, 2016.
Methods for action recognition have evolved considerably over the past years and can now automatically learn and recognize short term actions with satisfactory accuracy. Nonetheless, the recognition of complex activities - compositions of actions and scene objects - is still an open problem due to the complex temporal and composite struct...More
Full Text (Upload PDF)
PPT (Upload PPT)