EMBEDDIA - Cross-Lingual Embeddings for Less-Represented Languages in European News Media
Published March 25, 2022 | Version v1
Conference paper Open

Visual Topic Modelling for NewsImage Task at MediaEval 2021

Authors/Creators

  • 1. University of Helsinki, Helsinki, Finland

Description

We present the Visual Topic Model (VTM)—a model able to generate a topic distribution for an image, without using any text during inference. The model is applied to an image-text matching task at MediaEval 2021. Though results for this specific task are negative (the model works worse than a baseline), we demonstrate that VTM produces meaningful results and can be used in other applications

Files

MediaEval_WorkingNote.pdf

Files (563.9 kB)

Name Size
md5:d15c969d31626d13df3e98e4879b2e02
563.9 kB Preview Download

Additional details

Funding

European Commission
EMBEDDIA - Cross-Lingual Embeddings for Less-Represented Languages in European News Media 825153