We present a novel model for human action categorization. A video sequence is represented as a collection of spatial and spatial-temporal features by extracting static and dynamic...
The work described here initially formed part of a triangulation exercise to establish the effectiveness of the Query Term Order algorithm. The methodology produced subsequently p...
: In the last decade, many evaluation results have been created within the evaluation initiatives like TREC, NTCIR and CLEF. The large amount of data available has led to substanti...
Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
We present the Recursive Least Squares Dictionary Learning Algorithm, RLSDLA, which can be used for learning overcomplete dictionaries for sparse signal representation. Most Dicti...