In this paper, we propose an algorithm for sustained tracking of humans, where we combine frame-to-frame articulated motion estimation with a per-frame body detection algorithm. T...
In this paper we propose an approach for action recognition based on a vocabulary of local motion-appearance features and fast approximate search in a large number of trees. Large...
The problem of automatic recognition of human activities is among the most important and challenging open areas of research in Computer Vision. This paper presents a new approach ...
Arcangelo Distante, I. Gnoni, Marco Leo, Paolo Spa...
— In an effort to ease the burden of programming motor commands for humanoid robots, a computer vision technique is developed for converting a monocular video sequence of human p...
Jeffrey B. Cole, David B. Grimes, Rajesh P. N. Rao
In this paper, we present an efficient system for action recognition from very short sequences. For action recognition typically appearance and/or motion information of an action ...