Current image retrieval systems do not provide users with adequate interfaces able to reduce the semantic gap existing between the high-level semantics of images (as perceived by t...
Abstract This paper presents an approach to designing and implementing extensible computational models for perceiving systems based on a knowledge-driven joint inference approach. ...
Contextual information is vital for the robust extraction of semantic information in automated surveillance systems. We have developed a scene independent framework for the detect...
Shape of an object is an important feature for image and multimedia similarity retrievals. In our previous studies we introduced a new boundary-based technique (MBC-based) for shap...
We describe a scalable approach to 3D smooth object retrieval which searches for and localizes all the occurrences of a user outlined object in a dataset of images in real time. T...