Learning from Ambiguously Labeled Face Images

Learning a classifier from ambiguously labeled face images is challenging since training images are not always explicitly-labeled. For instance, face images of two persons in a news photo are not explicitly labeled by their names in the caption. We propose a Matrix Completion for Ambiguity Resolutio...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 40(2018), 7 vom: 01. Juli, Seite 1653-1667
1. Verfasser:	Chen, Ching-Hui (VerfasserIn)
Weitere Verfasser:	Patel, Vishal M, Chellappa, Rama, Ching-Hui Chen
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2018
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article Research Support, U.S. Gov't, Non-P.H.S.