Discrete Visual Perception

Abstract : Computational vision and biomedical image have made tremendous progress of the past decade. This is mostly due the development of efficient learning and inference algorithms which allow better, faster and richer modeling of visual perception tasks. Graph-based representations are among the most prominent tools to address such perception through the casting of perception as a graph optimization problem. In this paper, we briefly introduce the interest of such representations, discuss their strength and limitations and present their application to address a variety of problems in computer vision and biomedical image analysis.
Liste complète des métadonnées

Cited literature [72 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01023406
Contributor : Paragios Nikos <>
Submitted on : Wednesday, July 16, 2014 - 8:33:52 PM
Last modification on : Thursday, February 7, 2019 - 5:29:19 PM
Document(s) archivé(s) le : Thursday, November 20, 2014 - 6:17:46 PM

File

icprv2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01023406, version 1

Citation

Nikos Paragios, Nikos Komodakis. Discrete Visual Perception. International Conference on Pattern Recognition, Aug 2014, Stockholm, Sweden. pp.1-7. ⟨hal-01023406⟩

Share

Metrics

Record views

562

Files downloads

452