This paper presents an approach for human activity recognition by representing the frames of the video sequence with the distribution of local motion features and their spatiotemp...
This paper presents a spatiotemporal pyramid representation for recognizing facial expressions and hand gestures. This approach works by partitioning video sequence into increasin...
Human activity recognition and speech recognition appear to be two loosely related research areas. However, on a careful thought, there are several analogies between activity and ...
This work addresses the problem of human action recognition by introducing a representation of a human action as a collection of short trajectories that are extracted in areas of ...
Antonios Oikonomopoulos, Ioannis Patras, Maja Pant...
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...