BCMF: A bidirectional cross-modal fusion model for fake news detection
作者:
Highlights:
• We propose a novel model, namely BCMF, for fake news detection.
• BCMF leverages both contextualized visual embeddings and bi-directional fusions.
• We propose a bi-directional cross-modal aggregation mechanism to deeply fuse the visual and textual information.
• The model outperforms most of the state-of-the-art methods on four datasets.
• The research sheds light on the role of bidirectional cross-modal fusion.
摘要
•We propose a novel model, namely BCMF, for fake news detection.•BCMF leverages both contextualized visual embeddings and bi-directional fusions.•We propose a bi-directional cross-modal aggregation mechanism to deeply fuse the visual and textual information.•The model outperforms most of the state-of-the-art methods on four datasets.•The research sheds light on the role of bidirectional cross-modal fusion.
论文关键词:Fake news detection,Cross-modal fusion,Contextualized embedding,Deep learning
论文评审过程:Received 28 April 2022, Revised 21 July 2022, Accepted 12 August 2022, Available online 19 August 2022, Version of Record 19 August 2022.
论文官网地址:https://doi.org/10.1016/j.ipm.2022.103063