Unsupervised Manifold Learning for Video Genre Retrieval

Unsupervised Manifold Learning for Video Genre Retrieval

Author Almeida, Jurandy Autor UNIFESP Google Scholar
Pedronette, Daniel Carlos Guimarães Google Scholar
Penatti, Otavio Augusto Bizetto Google Scholar
Bayro-Corrochano, Eduardo Google Scholar
Hancock, Edwin Google Scholar
Institution Universidade Federal de São Paulo (UNIFESP)
Abstract This paper investigates the perspective of exploiting pairwise similarities to improve the performance of visual features for video genre retrieval. We employ manifold learning based on the reciprocal neighborhood and on the authority of ranked lists to improve the retrieval of videos considering their genre. A comparative analysis of different visual features is conducted and discussed. We experimentally show in the dataset of 14,838 videos from the MediaEval benchmark that we can achieve considerable improvements in results. In addition, we also evaluate how the late fusion of different visual features using the same manifold learning scheme can improve the retrieval results.
Keywords video genre retrieval
ranking methods
manifold learning
Language English
Date 2014-01-01
Published in Progress In Pattern Recognition Image Analysis, Computer Vision, And Applications, Ciarp 2014. Berlin: Springer-verlag Berlin, v. 8827, p. 604-612, 2014.
ISSN 0302-9743 (Sherpa/Romeo, impact factor)
Publisher Springer
Extent 604-612
Origin http://dx.doi.org/10.1007/978-3-319-12568-8_74
Access rights Closed access
Type Conference paper
Web of Science ID WOS:000346407400074
URI http://repositorio.unifesp.br/11600/45140

Show full item record


File Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)




My Account