We systematically evaluate a recently proposed method for unsupervised discrimination power analysis for feature selection and optimization in multimedia applications. A series of...
Abstract. The semantic contextual information is shown to be an important resource for improving the scene and image recognition, but is seldom explored in the literature of previo...
This paper proposes a method for automatically inserting commas into Japanese texts. In Japanese sentences, commas play an important role in explicitly separating the constituents...
This paper introduces a supervised discriminant Hausdorff distance that fits into the framework for automatic face analysis and recognition proposed in [1]. Our proposal relies so...
This paper describes an interactive vision system for a robot that finds an object specified by a user and brings it to the user. The system first registers object models automati...