Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

10-2013

Abstract

Hierarchical classification (HC) is a popular and efficient way for detecting the semantic concepts from the images. However, the conventional HC, which always selects the branch with the highest classification response to go on, has the risk of propagating serious errors from higher levels of the hierarchy to the lower levels. We argue that the highestresponse-first strategy is too arbitrary, because the candidate nodes are considered individually which ignores the semantic relationship among them. In this paper, we propose a novel method for HC, which is able to utilize the semantic relationship among candidate nodes and their children to recover the responses of unreliable classifiers of the candidate nodes, with the hope of providing the branch selection a more globally valid and semantically consistent view. The experimental results show that the proposed method outperforms the conventional HC methods and achieves a satisfactory balance between the accuracy and efficiency.

Keywords

Concept detection, Error propagation, Large-scale hierarchy

Discipline

Data Storage Systems | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

MM '13: Proceedings of the 21st ACM International Conference on Multimedia: October 21-25, Barcelona, Spain

First Page

697

Last Page

700

ISBN

9781450324045

Identifier

10.1145/2502081.2502182

Publisher

ACM

City or Country

Barcelona, Spain

Download

Share

COinS