This paper introduces a new feature-based technique for implicitly modelling objects in visual surveillance. Previous work has generally employed background subtraction and other ...
A lot of future-related information is available in news articles or Web pages. This information can however differ to large extent and may fluctuate over time. It is therefore di...
Adam Jatowt, Kensuke Kanazawa, Satoshi Oyama, Kats...
We report experiments on the use of standard natural language processing (NLP) tools for the analysis of music lyrics. A significant amount of music audio has lyrics. Lyrics enco...
Jose P. G. Mahedero, Alvaro Martinez, Pedro Cano, ...
This paper investigates the level of metadata accuracy required for image filters to be valuable to users. Access to large digital image and video collections is hampered by ambig...
Many visual search and matching systems represent images using sparse sets of "visual words": descriptors that have been quantized by assignment to the best-matching symb...