This article deals with a biologically-motivated three-level computational attention model architecture based on the rarity and the information theory framework. It mainly focuses on low-level and mediumlevel steps and their application in pre-attentive detection of tumours in CT scans and unusual events in audio recordings.
Mancas, M., Couvreur, L., Gosselin, B., & Macq, B. (2007). Computational Attention for Event Detection. In Applied Computer Science Group Bielefeld University, Germany (ed.), Proceedings of the 5th International Conference on Computer Vision Systems. Applied Computer Science Group Bielefeld University. https://hdl.handle.net/2078.5/59709