DeteRel “Detecting Relationships between Entities in Unstructured and Structured Data”, owner National University of Science and Technology Politehnica Bucharest (led by AI Multimedia Lab), partners Ferdinand I Military Technical Academy, Romanian Ministry of National Defence — Military Equipment and Technologies Research Agency, Softrust Vision Analytics SRL, public beneficiary Romanian Intelligence Service, funded by UEFISCDI, Solutions Axis, grant PN-IV-P6-6.3-SOL-2024-0060, agreement SOL12/2024 (budget ~800k Eur, 2024-2026).
Objectives:
The general objective of the project is to develop a software platform with biometric comparison functionalities for image and audio data, enabling the detection of relationships between consolidated entities (entity resolution). These entities will be extracted from structured data or identified within unstructured data (primarily text, images, audio, and video). The platform will achieve this through semantic analysis of texts, image and video descriptions, and transcripted recordings, as well as by correlating associated metadata or contextual information generated through the interpretation of multimedia data.
