Aus Aifbportal
Wechseln zu:Navigation, Suche

Multi-Modal Correlated Centroid Space for Multi-Lingual Cross-Modal Retrieval

Multi-Modal Correlated Centroid Space for Multi-Lingual Cross-Modal Retrieval

Published: 2015 April
Herausgeber: Hanbury, Allan and Kazai, Gabriella and Rauber, Andreas and Fuhr, Norbert
Buchtitel: Advances in Information Retrieval: 37th European Conference on IR Research (ECIR), Vienna, Austria.
Verlag: Springer International Publishing
Erscheinungsort: Cham, Germany

Referierte Veröffentlichung


We present a novel cross-modal retrieval approach where the textual modality is present in different languages. We retrieve semantically similar documents across modalities in different languages using a correlated centroid space unsupervised retrieval (C2SUR) approach. C2SUR consists of two phases. In the first phase, we extract heterogeneous features from a multi-modal document and project it to a correlated space using kernel canonical correlation analysis (KCCA). In the second phase, correlated space centroids are obtained using clustering to retrieve cross-modal documents with different similarity measures. Experimental results show that C2SUR outperforms the existing state-of-the-art English cross-modal retrieval approaches and achieve similar results for other languages.

Weitere Informationen unter: Link
DOI Link: 10.1007/978-3-319-16354-3_9




Web Science und Wissensmanagement


Maschinelles Lernen, Multimedia Annotation & Retrieval