Comparison of Feature Sets Using Multimedia Translation

Comparison of Feature Sets Using Multimedia Translation

Feature selection is very important for many computer vision applications. However, it is hard to find a good measure for the comparison. In this study, feature sets are compared using the translation model of object recognition which is motivated by the availablity of large annotated data sets. Ima...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Duygulu, Pınar, Özcanlı, Özge Can, Papernick, Norman
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Applied sciences
Computer science
control theory
systems
Content Base Image Retrieval
Exact sciences and technology
Image Region
Machine Translation
Software
Statistical Machine Translation
Target Distribution
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Feature selection is very important for many computer vision applications. However, it is hard to find a good measure for the comparison. In this study, feature sets are compared using the translation model of object recognition which is motivated by the availablity of large annotated data sets. Image regions are linked to words using a model which is inspired by machine translation. Word prediction performance is used to evaluate large numbers of images.
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-540-39737-3_64