Skip to Main content Skip to Navigation
Conference papers

Clustering based re-scoring for semantic indexing of multimedia documents.

Abdelkader Hamadi 1 Georges Quénot 1 Philippe Mulhem 1
1 LIG - Laboratoire d'Informatique de Grenoble
Abstract : This paper describes a new approach for multime- dia documents indexing and addresses the problem of automati- cally detecting a large number of visual concepts. Though using a multi-label approaches are used in some works, concepts detectors are often trained independently. We propose a model that takes into account the detection of not only a target concept but also other ones and regroups in terms of semantics similar samples. The expected benefit from such a combination is to consider the relationships between concepts in order to reclassify the results of an initial indexing system. Experiments on the TRECVID 2012 data are presented and discussed. Our method has significantly improved a quite good baseline system performance up to +6% on mean average precision.
Keywords : image classification image sensors indexing information retrieval learning (artificial intelligence) ontologies (artificial intelligence) semantic networks support vector machines video retrieval KNN classifier MAP measurement MSVM TRECVID 2012 data conce
Document type :
Conference papers
Complete list of metadata
https://hal.inria.fr/hal-00953084
Contributor : Marie-Christine Fauvet <>
Submitted on : Friday, February 28, 2014 - 10:31:41 AM
Last modification on : Thursday, November 19, 2020 - 12:59:40 PM

Identifiers

  • HAL Id : hal-00953084, version 1

Collections

CNRS | UGA | LIG | LIG_TDCGE | LIG_TDCGE_MRIM

Citation

Abdelkader Hamadi, Georges Quénot, Philippe Mulhem. Clustering based re-scoring for semantic indexing of multimedia documents.. Content-Based Multimedia Indexing (CBMI), 2013 11th International Workshop on, 2013, Veszprém, Hungary. pp.41-46. ⟨hal-00953084⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

199

 

Contact                    Legal Notice                    Personal Data