User menu

Accès à distance ? S'identifier sur le proxy UCLouvain | Saint-Louis

Computational Attention for Event Detection

Primary tabs

Mancas, Matei [FPMs] Couvreur, Laurent [FPMs] Gosselin, Bernard [FPMs] Macq, Benoît [UCL]

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.

Document type Communication à un colloque (Conference Paper)
Publication date 2007
Language Anglais
Conference "The 5th International Conference on Computer Vision Systems, 2007", Bielefeld (GERMANY) (du 21/03/2007 au 24/03/2007)
Host document Applied Computer Science Group Bielefeld University, Germany ; "Proceedings of the 5th International Conference on Computer Vision Systems" (ISBN : 978-3-00-020933-8)
Publisher Applied Computer Science Group Bielefeld University (Bielfeld (Germany))
Affiliations FPMs - TCTS
UCL - FSA/ELEC - Département d'électricité
Keywords SIGN
Links
Bibliographic reference Mancas, Matei ; Couvreur, Laurent ; Gosselin, Bernard ; Macq, Benoît. Computational Attention for Event Detection.The 5th International Conference on Computer Vision Systems, 2007 (Bielefeld (GERMANY), du 21/03/2007 au 24/03/2007). In: Applied Computer Science Group Bielefeld University, Germany, Proceedings of the 5th International Conference on Computer Vision Systems, Applied Computer Science Group Bielefeld University : Bielfeld (Germany)2007
Permanent URL http://hdl.handle.net/2078.1/90839