BibTeX

@inProceedings{raj-etal-2022-cross-323886,
	title        = {Cross-modal Transfer Between Vision and Language for Protest Detection},
	abstract     = {Most of today’s systems for socio-political event detection are text-based, while an increasing amount of information published on the web is multi-modal. We seek to bridge this gap by proposing a method that utilizes existing annotated unimodal data to perform event detection in another data modality, zero-shot. Specifically, we focus on protest detection in text and images, and show that a pretrained vision-and-language alignment model (CLIP) can be leveraged towards this end. In particular, our results suggest that annotated protest text data can act supplementarily for detecting protests in images, but significant transfer is demonstrated in the opposite direction as well.},
	booktitle    = {Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE), pages 56-60, Abu Dhabi},
	author       = {Raj, Ria and Andréasson, Kajsa and Norlund, Tobias and Johansson, Richard and Lagerberg, Aron},
	year         = {2022},
	publisher    = {Association for Computational Linguistics},
}