Proceedings chapter
OA Policy
English

Exploiting Synergistic and Redundant Features for Multimedia Document Classification

Presented at

Hamburg (Germany)

Publication date

2008

Abstract

The task of multimedia document classification is challenging due to a diverse set of problems like a high dimensional, sparse and noisy features space, the unknown relevance of the features towards the classification target and the semantic gap between non-informative, low-level features and high-level semantic meanings. As a solution we propose a classification approach combined with feature selection and construction based on feature information interactions. This information-theoretic dependence measure can detect complex feature de pendencies in multi-variate settings. They help to find relevant and non-redundant features and hence allow efficient classification. Experiments on artificial and real world data show the superiority of feature selection based on N-way interactions over greedy, pair-wise dependence measures like correlation and mutual information.

Keywords

  • Image clustering
  • latent semantic analysis
  • longterm learning
  • relevance feedback

Citation (ISO format)

KLUDAS, Jana, BRUNO, Eric, MARCHAND-MAILLET, Stéphane. Exploiting Synergistic and Redundant Features for Multimedia Document Classification. In: 32nd Annual Conference of the German Classification Society - Advances in Data Analysis, Data Handling and Business Intelligence (GfKl 2008). Hamburg (Germany). [s.l.] : [s.n.], 2008.

Main files (1)

Proceedings chapter (Accepted version)

Identifiers

  • PID : unige:47674
527views
196downloads

Technical informations

Creation

06/03/2015 17:12:06

First validation

06/03/2015 17:12:06

Update

13/10/2025 21:41:01

Status update

14/03/2023 22:58:33

Last indexation

03/12/2025 07:38:08
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated