—Graphics artists commonly employ physically-based simulation for the generation of effects such as smoke, explosions, and similar phenomena. The task of finding the correct par...
We present spatio-temporal feature descriptors that can be inferred from video and used as building blocks in action recognition systems. They capture the evolution of ``elementar...
We address recognition and localization of human actions in realistic scenarios. In contrast to the previous work studying human actions in controlled settings, here we train and ...
We model the spatio-temporal variations of the shape of objects in a video sequence using a unique SVD-like decomposition. The decomposition is used to compute shape features, whi...
The growing availability of mobile devices produces an enormous quantity of personal tracks which calls for advanced analysis methods capable of extracting knowledge out of massiv...