Zur Seitenansicht
 

Titelaufnahme

Titel
Exploiting Contextual Knowledge for Hybrid Classification of Visual Objects
Verfasser / Verfasserin Eiter, Thomas ; Kaminski, Tobias
Erschienen in
Logics in Artificial Intelligence - 15th European Conference, JELIA 2016, Larnaca, Cyprus, November 9-11, 2016, Proceedings / Michael, Loizos; Kakas, Antonis C., 15th European Conference, JELIA 2016, Larnaca, Cyprus, 2016, S. 223-239
Erschienen2016
SpracheEnglisch
SerieLecture Notes in Computer Science ; 10021
DokumenttypAufsatz in einem Sammelwerk
Schlagwörter (EN)Knowledge Representation / Answer Set Programming / Machine Learning / Constraints
Projekt-/ReportnummerFWF project P27730
Projekt-/ReportnummerFWF project W1255-N23
ISBN9783319487571
URNurn:nbn:at:at-ubtuw:3-3056 Persistent Identifier (URN)
DOI10.1007/978-3-319-48758-8_15 
Zugriffsbeschränkung
 Das Werk ist frei verfügbar
Dateien
Exploiting Contextual Knowledge for Hybrid Classification of Visual Objects [3.3 mb]
Links
Nachweis
Klassifikation
Zusammenfassung (Englisch)

We consider the problem of classifying visual objects in a scene by exploiting the semantic context. For this task, we define hybrid classifiers (HC) that combine local classifiers with context constraints, and can be applied to collective classification problems (CCPs) in general. Context constraints are represented by weighted ASP constraints using object relations. To integrate probabilistic information provided by the classifier and the context, we embed our encoding in the formalism LP^MLN, and show that an optimal labeling can be efficiently obtained from the corresponding LP^MLN program by employing an ordinary ASP solver. Moreover, we describe a methodology for constructing an HC for a CCP, and present experimental results of applying an HC for object classification in indoor and outdoor scenes, which exhibit significant improvements in terms of accuracy compared to using only a local classifier.

Notiz
Notiz
Statistik
Das PDF-Dokument wurde 36 mal heruntergeladen.