Bag-of-multimedia-words for image classification

We introduce the bag-of-multimedia-words model that tightly combines the heterogeneous information coming from the text and the pixel-based information of a multimedia document. The proposed multimedia feature generation process is generic for any multi-modality and aims at enriching a multimedia do...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the 21st International Conference on Pattern Recognition (ICPR2012) pp. 1509 - 1512
Main Authors Znaidia, A., Shabou, A., Le Borgne, H., Hudelot, C., Paragios, N.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2012
Subjects
Encoding
Multimedia communication
Training
Vectors
Videos
Visualization
Vocabulary
Online AccessGet full text

Cover

More Information
Summary:We introduce the bag-of-multimedia-words model that tightly combines the heterogeneous information coming from the text and the pixel-based information of a multimedia document. The proposed multimedia feature generation process is generic for any multi-modality and aims at enriching a multimedia document description with compact and discriminative signatures well appropriate to linear classifiers. It is evaluated on the Pascal VOC 2007 classification challenge, outperforming the state-of-the-art bag-of-visual-words or bag-of-tag-words based classification approaches.
ISBN:9781467322164
1467322164
ISSN:1051-4651
2831-7475