This paper presents a scalable scene parsing algorithm based on image retrieval and superpixel matching. We fo-cus on rare object classes, which play an important role in achieving richer semantic understanding of visual scenes, compared to common background classes. Towards this end, we make two

(20 pages (limit: 20 pages)) Abstract: We present a modular architecture for image understanding and ac-tive computer vision which consists of three major components: Sensor and actor interfaces required for data{driven active vision are encapsulated to hide machine{dependent parts; image

representative photos of the given concept for representative local regions from a large-scale unorganized collection of consumer-generated geotagged photos. The results help us understand how objects, scenes or events corresponding to the same given concept are visually different depending on local regions over

The task of extracting a semantic video object is split into two subproblems, namely, object segmentation and region segmentation. Object segmentation relies on aprioriassumptions, whereas region segmentation is data-driven and can be solved in an automatic manner. These two subproblems

Computer vision, Pattern recognition, Multimedia data mining Specifically, learning from large scale multi-modal data; leveraging noisy web images and videos for semi-supervised learning; large scale object, scene and face recognition; semantic analysis and retrieval of large multi

. Participants with ASD were recruited (a) via an advertisement on the "Research Projects: Be a Participant" page of The National Autistic Society U.K. Web site (www.autism.org.uk), (b) through local ASD support groups, (c) through the Durham University Service for Students with Disabilities, and (d

available for use. Such modeling algorithms are data-driven and concentrate on specific features of the objects, being accessible to numerical models. We present an approach that brings the human expert knowledge about the scene, the objects inside, and their representation by the data and the behavior

Digitising statistics handling through

in understanding and leveraging the role of provenance as well as trust in data integration and data management. My research demonstrates the synergistic use of artificial intelligence, Semantic Web, and database theory to address three aspects of provenance and trust management namely, (a) Modeling, (b) Querying

First, I would like to thank to Dimka Karastoyanova and Mariano Cilia for all the fruitful discussions, their guidance and support through the course of this project. Thanks also to Prof. Alejandro Buchmann who sponsored my stay at Technische Universität Darmstadt during the spring of 2004. The special thanks go to my advisor, Mariano Cilia, who has made all this possible. Finally, I’d like to thank to my family for all these years of support.