SimRank similarity preserving projection for shape‐based 3D model auto‐annotation

We present a new dimensionality reduction method, called SimRank similarity preserving projection (SSPP), that finds a subspace preserving semantic similarity among data represented with SimRank similarity on a bipartite graph. The relationship between 3D models and keywords in a tagged 3D model dat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEJ transactions on electrical and electronic engineering 2018-02, Vol.13 (2), p.341-342
Hauptverfasser: Tatsuma, Atsushi, Aono, Masaki
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We present a new dimensionality reduction method, called SimRank similarity preserving projection (SSPP), that finds a subspace preserving semantic similarity among data represented with SimRank similarity on a bipartite graph. The relationship between 3D models and keywords in a tagged 3D model dataset is represented with bipartite graph. For shape‐based 3D model auto‐annotation, we try to capture the relationship of tagged 3D models by SSPP. Experimental results show that our method outperforms the baseline and previous methods.
ISSN:1931-4973
1931-4981
DOI:10.1002/tee.22532