Abstract This paper focuses on human behavior recognition where the main problem is to bridge the semantic gap between the analogue observations of the real world and the symbolic ...
A new, linguistically annotated, video database for automatic sign language recognition is presented. The new RWTH-BOSTON-400 corpus, which consists of 843 sentences, several spea...
Philippe Dreuw, Carol Neidle, Vassilis Athitsos, S...
Present work introduces a probabilistic recognition scheme for hand gestures. Self organizing feature maps are used to model spatiotemporal information extracted through image proc...
George Caridakis, Christos Pateritsas, Athanasios ...
Indexing echocardiogram videos at different levels of structure is essential for providing efficient access to their content for browsing and retrieval purposes. We present a nove...
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...