MUMOSA, Interactive Dashboard for MUlti-MOdal Situation Awareness

Thumbnail Image

Files

2024.futured1.4.pdf (3.47 MB)

Links to Files

https://aclanthology.org/2024.futured-1.4

Permanent Link

https://doi.org/10.18653/v1/2024.futured-1.4
 http://hdl.handle.net/11603/37089

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0003-1383-8120

Date

2024-11

Type of Work

conference papers and proceedings
Text

Department

Program

Citation of Original Publication

Lukin, Stephanie M., Shawn Bowser, Reece Suchocki, Douglas Summers-Stay, Francis Ferraro, Cynthia Matuszek, and Clare Voss. “MUMOSA, Interactive Dashboard for MUlti-MOdal Situation Awareness.” In Proceedings of the Workshop on the Future of Event Detection (FuturED), edited by Joel Tetreault, Thien Huu Nguyen, Hemank Lamba, and Amanda Hughes, 32–47. Miami, Florida, USA: Association for Computational Linguistics, 2024. https://aclanthology.org/2024.futured-1.4.

Rights

This work was written as part of one of the author's official duties as an Employee of the United States Government and is therefore a work of the United States Government. In accordance with 17 U.S.C. 105, no copyright protection is available for such works under U.S. Law.
Public Domain

Subjects

Abstract

Information extraction has led the way for event detection from text for many years. Recent advances in neural models, such as Large Language Models (LLMs) and Vision-Language Models (VLMs), have enabled the integration of multiple modalities, providing richer sources of information about events. Concurrently, the development of schema graphs and 3D reconstruction methods has enhanced our ability to visualize and annotate complex events. Building on these innovations, we introduce the MUMOSA (MUlti-MOdal Situation Awareness) interactive dashboard that brings these diverse resources together. MUMOSA aims to provide a comprehensive platform for event situational awareness, offering users a powerful tool for understanding and analyzing complex scenarios across modalities.