EUVIMEDEUVIMED entdecken
Crossref

Enhancing Emergency Post Classification through Image Information Amplification via Large Language Models

Pablo Giaccaglia, Carlo Alberto Bono, Barbara Pernici

Proceedings of the International ISCRAM Conference · 14.05.2024

DOI: 10.59297/x3m25n43 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the International ISCRAM Conference, online erschienen am 14.05.2024. Verfasst von Pablo Giaccaglia und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time information extracted from social media platforms can be highly valuable during emergencies. For example, reports and direct witnesses can help build situational awareness in the early phases of an emergency, with the potential to save lives. However, suitable techniques for selecting relevant data are needed to gather this information from large-scale social media streams and utilize it effectively. Given the multimedia nature of these streams, selection techniques should simultaneously understand textual and image information, as previous studies highlighted. Leveraging recent advances in language and vision models, we propose and evaluate a method working with a homogeneous, text-only representation for the different modalities of social media posts. Experiments on established and novel datasets, including video data, show that the proposed method achieves state-of-the-art performances while providing a highly general and plug-and-play approach to multimodal data filtering.

Zitieren

APA

Giaccaglia, P., Bono, C. A., & Pernici, B. (2024). Enhancing Emergency Post Classification through Image Information Amplification via Large Language Models. Proceedings of the International ISCRAM Conference. https://doi.org/10.59297/x3m25n43

Vancouver

Giaccaglia P, Bono CA, Pernici B. Enhancing Emergency Post Classification through Image Information Amplification via Large Language Models. Proceedings of the International ISCRAM Conference. 2024. doi:10.59297/x3m25n43

BibTeX
@article{Giaccaglia2024,
  author = {Giaccaglia, Pablo and Bono, Carlo Alberto and Pernici, Barbara},
  title = {Enhancing Emergency Post Classification through Image Information Amplification via Large Language Models},
  journal = {Proceedings of the International ISCRAM Conference},
  year = {2024},
  doi = {10.59297/x3m25n43}
}
Kostenlos starten →