Weakly Supervised Deep Matrix Factorization for Social Image Understanding

The number of images associated with weakly supervised user-provided tags has increased dramatically in recent years. User-provided tags are incomplete, subjective and noisy. In this paper, we focus on the problem of social image understanding, i.e., tag refinement, tag assignment, and image retriev...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing 2017-01, Vol.26 (1), p.276-288
Hauptverfasser:	Li, Zechao, Tang, Jinhui
Format:	Artikel
Sprache:	eng
Schlagworte:	Data models Deep architecture Image retrieval image tagging matrix factorization Noise measurement Semantics Sparse matrices Tagging Visualization weakly supervised
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!