Mining persons, objects and places of interest from heterogeneous data sources

• Grant number: 19/15825-1
• Support Opportunities: Scholarships in Brazil - Doctorate (Direct)
• Start date: August 01, 2019
• End date: November 30, 2023
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Anderson de Rezende Rocha
• Grantee: Gabriel Capiteli Bertocco
• Host 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
• Associated scholarship(s): 22/02299-2 - Self-supervised learning for biometrics and beyond, BE.EP.DD

Abstract

In this research, we aim at designing a framework to rank the frequency of the appearance of different individuals, objects or places based on text and visual information assets related to an event for further analysis. Moreover, we intend to (1) design and develop appropriate methods to search for some possible classes of interest (possible suspects, places, or objects of interest), while rejecting non-interesting classes/objects; and (2) develop human identification methods (e.g., face recognition) for such challenging and specific scenarios to identify possible suspects in an event. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

BERTOCCO, GABRIEL C.; ANDALO, FERNANDA; ROCHA, ANDERSON. Unsupervised and Self-Adaptative Techniques for Cross-Domain Person Re-Identification. IEEE Transactions on Information Forensics and Security, v. 16, p. 4419-4434, 2021. (19/15825-1, 17/12646-3)

BERTOCCO, GABRIEL; THEOPHILO, ANTONIO; ANDALO, FERNANDA; ROCHA, ANDERSON. Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution. IEEE Transactions on Information Forensics and Security, v. 18, p. 15-pg., 2023-01-01. (19/15825-1, 18/10204-6, 17/12646-3)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

BERTOCCO, Gabriel Capiteli. Aprendizado auto-supervisionado para re-identificação totalmente não-anotada em aplicações no mundo real. 2024. Doctoral Thesis - Universidade Estadual de Campinas (UNICAMP). Instituto de Computação Campinas, SP.