inria-00612277, version 2
Modeling Spatial Layout with Fisher Vectors for Image Categorization
Josip Krapac
a, 1Jakob Verbeek
a, 1Frédéric Jurie
1, 2
International Conference on Computer Vision (2011)
Résumé : We introduce an extension of bag-of-words image representations to encode spatial layout. Using the Fisher kernel framework we derive a representation that encodes the spatial mean and the variance of image regions associated with visual words. We extend this representation by using a Gaussian mixture model to encode spatial layout, and show that this model is related to a soft-assign version of the spatial pyramid representation. We also combine our representation of spatial layout with the use of Fisher kernels to encode the appearance of local features. Through an extensive experimental evaluation, we show that our representation yields state-of-the-art image categorization results, while being more compact than spatial pyramid representations. In particular, using Fisher kernels to encode both appearance and spatial layout results in an image representation that is computationally efficient, compact, and yields excellent performance while using linear classifiers.
- a – INRIA
- 1 : LEAR (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
- CNRS : FR71 – CNRS : UMR5527 – INRIA – Laboratoire Jean Kuntzmann – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
- 2 : Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen (GREYC)
- CNRS : UMR6072 – Université de Caen – Ecole Nationale Supérieure d'Ingénieurs de Caen
- Domaine : Informatique/Apprentissage
- Versions disponibles : v1 (29-07-2011) v2 (06-09-2011)
- inria-00612277, version 2
- http://hal.inria.fr/inria-00612277
- oai:hal.inria.fr:inria-00612277
- Contributeur : Jakob Verbeek
- Soumis le : Mardi 6 Septembre 2011, 12:03:49
- Dernière modification le : Mardi 6 Septembre 2011, 13:46:44







Documents associés
Exporter