The co-occurrence pattern, a combination of binary or local features, is more discriminative than individual features and has shown its advantages in object, scene, and action rec...
We present a novel method for analyzing social behavior. Continuous videos are segmented into action ‘bouts’ by building a temporal context model that combines features from s...
In this paper, we investigate the detection of semantic
human actions in complex scenes. Unlike conventional
action recognition in well-controlled environments,
action detection...
Abstract. We address the problem of learning good features for understanding video data. We introduce a model that learns latent representations of image sequences from pairs of su...
A feature extraction system based on artificial life concepts is presented. The system provides automatic character feature extraction through the local actions of autonomous feat...