Advanced search
Start date

Provenance filtering and analysis

Grant number: 20/02211-2
Support type:Scholarships in Brazil - Doctorate (Direct)
Effective date (Start): May 01, 2020
Effective date (End): November 30, 2022
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computer Systems
Principal Investigator:Anderson de Rezende Rocha
Grantee:João Phillipe Cardenuto
Home Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
Associated research grant:17/12646-3 - Déjà vu: feature-space-time coherence from heterogeneous data for media integrity analytics and interpretation of events, AP.TEM


In this research, we are mainly aimed at answering the question of how to find possible relationships among images from different moments in time (e.g., how different image pieces contribute to create a composite one). This research will allow the development of a series of solutions to analyze the provenance of a visual asset allowing us to check its veracity and to pinpoint the pieces that contributed to its creation process in the case of a composite/fake. Such tools will be invaluable for evaluating how different media objects are related digitally and physically, analyzing group dynamics, and even fact-checking published news articles using their pictures as a proxy for veracity checking against fake news. (AU)