The MIDI group works in the field of Big Data Management and Analytics, addressing topics that include integrating, mining, analyzing and querying large volumes of various types of data, ranging from structured and semi-structured data, to spatiotemporal data, text, image, video and 3D models. A particular emphasis is put on the design and use of Machine Learning techniques in contexts specific to data analysis and data processing problems, with a focus on the explainability and transparency of such algorithms. Applications include social media content and graph analytics, semantic web data integration and analysis, pattern detection in image, video and multimodal data, search engines for different types of data, knowledge extraction from data, data privacy, etc. The application domains are vast, such as cultural heritage, security, opinion mining, health, etc.
Indexing, analysis and research of visual content
Learning for computer vision
Massive data integration (Linked and Streaming data)
Analysis and mining of social networks (graph structure and text)
Mobility and spatio-temporal data analytics
Machine learning model explainability and transparency