Abstract. This paper describes a method of producing segmentation point candidates for on-line handwritten Japanese text by a support vector machine (SVM) to improve text recogniti...
In the novelty task on sentence level, the amount of information used in similarity computation is the major challenging issue. A shallow NLP approach extracts noun and verb featu...
In this paper, we propose a content based video categorizing method focusing broadcasted sports videos using camera motion parameters. We define two new features in the proposed m...
We address the issue of segmenting multiple textured objects in presence of a background texture. The proposed technique is based on Geodesic Active Contour (GAC) and can segment m...
Currently, most human action recognition systems are trained with feature sets that have no missing data. Unfortunately, the use of human pose estimation models to provide more des...
Patrick Peursum, Hung Hai Bui, Svetha Venkatesh, G...