We consider the problem of learning a mapping function from low-level feature space to high-level semantic space. Under the assumption that the data lie on a submanifold embedded ...
We investigate methods of segmenting, visualizing, and indexing presentation videos by both audio and visual data. The audio track is segmented by speaker, and augmented with key ...
In this project (VIRSI) we investigate the promising contentbased retrieval paradigm known as interactive search or relevance feedback, and aim to extend it through the use of syn...
Bart Thomee, Mark J. Huiskes, Erwin M. Bakker, Mic...
The state of the art for solving the phase retrieval problem in two dimensions relies heavily on the algorithms proposed by Gerchberg, Saxton, and Fienup. Despite the widespread u...
Heinz H. Bauschke, Patrick L. Combettes, D. Russel...
For the manual semantic markup of documents to become widespread, users must be able to express annotations that conform to ontologies (or schemas) that have shared meaning. Howev...