MétaCan
← tous les travaux

Supervised Learning of Semantic Classes for Image Annotation and Retrieval

2007· article· en· 870 citations· W2125238156 sur OpenAlex· 10.1109/tpami.2007.61

Pourquoi ce travail est-il dans la base ?

Une base qui oublie comment elle a trouvé un travail ne peut pas être vérifiée. Voici les voies qui ont admis celui-ci.

Organisme subventionnaire canadienUn organisme canadien l'a financé. Le travail peut ne porter aucune affiliation canadienne.

Aucune affiliation canadienne. Une base fondée sur la seule affiliation (le devis habituel) n'aurait jamais vu ce travail. C'est l'un des travaux qui justifient l'inversion de la base.

Résumé

A probabilistic formulation for semantic image annotation and retrieval is proposed. Annotation and retrieval are posed as classification problems where each class is defined as the group of database images labeled with a common semantic label. It is shown that, by establishing this one-to-one correspondence between semantic labels and semantic classes, a minimum probability of error annotation and retrieval are feasible with algorithms that are 1) conceptually simple, 2) computationally efficient, and 3) do not require prior semantic segmentation of training images. In particular, images are represented as bags of localized feature vectors, a mixture density estimated for each image, and the mixtures associated with all images annotated with a common semantic label pooled into a density estimate for the corresponding semantic class. This pooling is justified by a multiple instance learning argument and performed efficiently with a hierarchical extension of expectation-maximization. The benefits of the supervised formulation over the more complex, and currently popular, joint modeling of semantic label and visual feature distributions are illustrated through theoretical arguments and extensive experiments. The supervised formulation is shown to achieve higher accuracy than various previously published methods at a fraction of their computational cost. Finally, the proposed method is shown to be fairly robust to parameter tuning.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.

La notice

Revue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Thématique
Image Retrieval and Classification Techniques
Domaine
Computer Science
Établissements canadiens
Organismes subventionnaires
Natural Sciences and Engineering Research Council of CanadaGoogleNational Science Foundation
Mots-clés
Artificial intelligenceComputer scienceImage retrievalAutomatic image annotationPattern recognition (psychology)Feature (linguistics)Probabilistic logicAnnotationContextual image classificationClass (philosophy)Machine learningImage (mathematics)
Résumé présent dans OpenAlex
oui