TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Multi-modal subspace learning with dropout regularization for cross-modal recognition and retrieval

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2016 6th International Conference on Image Processing Theory, Tools and Applications (IPTA)
KustantajaIEEE
Sivut1-6
Sivumäärä6
ISBN (elektroninen)978-1-4673-8910-5
ISBN (painettu)978-1-4673-8911-2
DOI - pysyväislinkit
TilaJulkaistu - joulukuuta 2016
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational Conference on Image Processing Theory, Tools and Applications -
Kesto: 1 tammikuuta 1900 → …

Julkaisusarja

Nimi
ISSN (elektroninen)2154-512X

Conference

ConferenceInternational Conference on Image Processing Theory, Tools and Applications
Ajanjakso1/01/00 → …

Tiivistelmä

There has been a surge of efforts in cross-modal recognition and retrieval in recent multimedia research. Towards this goal, we investigate a multi-modal subspace learning algorithm together with the Dropout regularizer. Inspired by the regularization for neural networks, we propose to aritificially remove the effect of certain amount of feature bins using the probabilistic approach to prevent the linear subspace learning from over-fitting. The novel regularizer is well integrated into the multi-modal learning algorithm which maximizes the between-class scatter while minimizing the within-class scatter in the projected latent space. The new objective function can be solved efficiently as the generalized eigenvalue problem. Experimental results have shown that superior performance can be obtained in both face-sketch recognition and cross-modal retrieval applications.

Tutkimusalat

Julkaisufoorumi-taso