Transfer learning and mixed input deep neural networks for estimating flood severity in news content

Auteurs

P. Bruneau, and T. Tamisier

Référence

CEUR Workshop Proceedings, vol. 2670, 2019

Description

This paper describes deep learning approaches which use textual and visual features for flood severity detection in news content. In the context of the MediaEval 2019 Multimedia Satellite task, we test the value of transferring models pre-trained on large related corpora, as well as the improvement brought by dual branch models that combine embeddings output from mixed textual and visual inputs.

Lien

http://ceur-ws.org/Vol-2670/MediaEval_19_paper_48.pdf

Partager cette page :