We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective func...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
This paper presents a method for human action recognition based on patterns of motion. Previous approaches to action recognition use either local features describing small patches...
—In this paper we evaluate the use of Restricted Bolzmann Machines (RBM) in the context of learning and recognizing human actions. The features used as basis are binary silhouett...
Manuel Jesus Marin-Jimenez, Nicolas Perez De La Bl...
In interest point based human action recognition, local descriptors are used to represent information in the neighbourhood around each extracted space-time interest point. The per...