Spatial Intelligence in Multimedia Analytics (SpIMA)

Georeferenced multimedia data, like satellite imagery and videos, is vital for Earth Observation, urban computing, and lifelogging. However, managing this data is challenging due to its diversity and complexity. Deep learning and multimodal analytics offer promising solutions to unlock its potential. The special session focuses on merging spatial information with other data modalities to enrich the original data. It also explores using foundation models, such as large language models, in spatial AI to enhance interpretability and performance. Integrating these models can offer new insights from georeferenced multimedia datasets. Although cross-modal retrieval and image captioning are thriving, their integration into location-based services is relatively unexplored. Nevertheless, interpretable machine learning techniques are essential for extracting insights from multimodal geospatial data. The SpIMA special session aims to unite various communities working on georeferenced data and foster the exchange of ideas and methods.

The SpIMA special session will explore the following main topics, which include but are not restricted to:

Multimodal analytics and retrieval techniques for georeferenced multimedia data
Utilization of foundation models in spatial AI for interpretability, understanding, and explainability in artificial intelligence applied to georeferenced multimedia data
Cross-modal retrieval, image captioning, image generation, and visual question answering for location-based services
Satellite image analysis and retrieval
Semantically-aware approaches for handling highly heterogeneous, distributed and semantically fragmented georeferenced multimedia data
Interpretable machine learning techniques for unlocking hidden knowledge in big georeferenced multimedia data
Digital Twins based on georeferenced multimedia
Applications of georeferenced multimedia data in urban and lifelog computing
Big data analytics and visualization on GIS platforms for georeferenced multimedia data

Important Dates

Special Session Paper Submission: ~~22 July 2024~~ 19 August 2024 (Extended)
Notification: 24 September 2024
Camera Ready Submission: 23 October 2024
Conference: 7-10 January 2025

Submission

The content is restricted to 12 pages, encompassing all figures, tables, and appendices, following the Springer LNCS style guidelines. An additional allowance of 2 pages exclusively for cited references is permitted. This aligns with the guidelines set for the main conference of MMM2025.

Organizers

Maria Pegia, Centre for Research and Technology Hellas, Information Technologies Institute, Greece
Ioannis Papoutsis, National Technical University of Athens, Greece
Ilias Gialampoukidis, Centre for Research and Technology Hellas, Information Technologies Institute, Greece
Björn Þór Jónsson, Department of Computer Science, Reykjavik University, Iceland
Demir Begüm, Department of Computer Science, TU Berlin, Germany
Stefanos Vrochidis, Centre for Research and Technology Hellas, Information Technologies Institute, Greece