Share Email Print
cover

Proceedings Paper

Multimodal visual dictionary learning via heterogeneous latent semantic sparse coding
Author(s): Chenxiao Li; Guiguang Ding; Jile Zhou; Yuchen Guo; Qiang Liu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Visual dictionary learning as a crucial task of image representation has gained increasing attention. Specifically, sparse coding is widely used due to its intrinsic advantage. In this paper, we propose a novel heterogeneous latent semantic sparse coding model. The central idea is to bridge heterogeneous modalities by capturing their common sparse latent semantic structure so that the learned visual dictionary is able to describe both the visual and textual properties of training data. Experiments on both image categorization and retrieval tasks demonstrate that our model shows superior performance over several recent methods such as K-means and Sparse Coding.

Paper Details

Date Published: 4 November 2014
PDF: 9 pages
Proc. SPIE 9273, Optoelectronic Imaging and Multimedia Technology III, 92731K (4 November 2014); doi: 10.1117/12.2073276
Show Author Affiliations
Chenxiao Li, Tsinghua Univ. (China)
Guiguang Ding, Tsinghua Univ. (China)
Jile Zhou, Tsinghua Univ. (China)
Yuchen Guo, Tsinghua Univ. (China)
Qiang Liu, Tsinghua Univ. (China)


Published in SPIE Proceedings Vol. 9273:
Optoelectronic Imaging and Multimedia Technology III
Qionghai Dai; Tsutomu Shimura, Editor(s)

© SPIE. Terms of Use
Back to Top