Learning semantic categories for 3D model retrieval

  • Authors:
  • Ryutarou Ohbuchi;Akihiro Yamamoto;Jun Kobayashi

  • Affiliations:
  • University of Yamanashi, Kofu-shi, Yamanashi-ken, Japan;University of Yamanashi, Kofu-shi, Yamanashi-ken, Japan;University of Yamanashi, Kofu-shi, Yamanashi-ken, Japan

  • Venue:
  • Proceedings of the international workshop on Workshop on multimedia information retrieval
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

A shape similarity judgment among a pair of 3D models is often influenced by their semantics, in addition to their shapes. If we could somehow incorporate semantic knowledge into a "shape similarity" comparison method, retrieval performance of a shape-based 3D model retrieval system could be improved. This paper presents a 3D model retrieval method that successfully incorporates semantic information from human-made categories (labels) in a training database. Our off-line, 2-stage semi-supervised approach learns efficiently from a small set of labeled models. The method first performs unsupervised learning from a large set of unlabeled 3D models to find a non-linear subspace on which the shape features are distributed. It then performs a supervised learning from a much smaller set of labeled 3D models to learn multiple semantic categories at once. Our experimental evaluation showed that the retrieval performance using proposed method is significantly higher than those of both supervised-only and unsupervised-only learning methods.