Improving Image Classification Using Semantic Attributes - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue International Journal of Computer Vision Année : 2012

Improving Image Classification Using Semantic Attributes

Résumé

The Bag-of-Words (BoW) model - commonly used for image classification - has two strong limitations: on one hand, visual words lack semantic meanings, on the other hand, they are often polysemous. This paper proposes to address these two limitations by introducing an intermediate representation based on the use of semantic attributes. Specifically, two different approaches are proposed. Both approaches consist of predicting a set of semantic attributes for the entire images as well as for local image regions, and in using these predictions to build the intermediate level features. Experiments on four challenging image databases (PASCAL VOC 2007, Scene-15, MSRCv2 and SUN-397) show that both approaches improve performance of the BoW model significantly. Moreover, their combination achieves state-of-the-art results on several of these image databases.
Fichier principal
Vignette du fichier
12_SEMATR_IJCV.pdf (1.59 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00805996 , version 1 (29-03-2013)

Identifiants

Citer

Yu Su, Frédéric Jurie. Improving Image Classification Using Semantic Attributes. International Journal of Computer Vision, 2012, 100 (1), pp.59-77. ⟨10.1007/s11263-012-0529-4⟩. ⟨hal-00805996⟩
253 Consultations
533 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More