OBJECTIVE VALIDATION OF A DYNAMICAL AND PLAUSIBLE COMPUTATIONAL MODEL OF VISUAL ATTENTION

Abstract : Building a generic and performant vision system is still an open research problem. Actually, real-world vision systems need to face the challenge of dimensionality and ambiguity of data. To tackle this problem, we introduce a dynamic computational attention model. This latter selects the most salient scene information while being able to adapt its behaviour to the needs of a generic vision system. We focus validation on plusibility, to check this property we compare through three measures results obtained by several algorithms and ground thruth.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00617730
Contributor : Vincent Courboulay <>
Submitted on : Tuesday, October 18, 2011 - 4:05:37 PM
Last modification on : Wednesday, September 11, 2019 - 11:00:13 AM
Long-term archiving on : Monday, December 5, 2016 - 3:10:55 AM

File

euvip_perreira.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Matthieu Perreira da Silva, Vincent Courboulay, Pascal Estraillier. OBJECTIVE VALIDATION OF A DYNAMICAL AND PLAUSIBLE COMPUTATIONAL MODEL OF VISUAL ATTENTION. IEEE European workshop on visual information processing, Jul 2011, Paris, France. pp.223-228, ⟨10.1109/EuVIP.2011.6045511⟩. ⟨hal-00617730⟩

Share

Metrics

Record views

177

Files downloads

173