Go to page
 

Bibliographic Metadata

Title
Exploiting Contextual Knowledge for Hybrid Classification of Visual Objects
AuthorEiter, Thomas ; Kaminski, Tobias
Published 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, page 223-239
Published2016
LanguageEnglish
SeriesLecture Notes in Computer Science ; 10021
Document typeArticle in a collected edition
Keywords (EN)Knowledge Representation / Answer Set Programming / Machine Learning / Constraints
Project-/ReportnumberFWF project P27730
Project-/ReportnumberFWF project W1255-N23
ISBN978-3-319-48757-1
URNurn:nbn:at:at-ubtuw:3-3056 Persistent Identifier (URN)
DOI10.1007/978-3-319-48758-8_15 
Restriction-Information
 The work is publicly available
Files
Exploiting Contextual Knowledge for Hybrid Classification of Visual Objects [3.3 mb]
Links
Reference
Classification
Abstract (English)

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.

Note
Note