Heterogeneous data analysis for event detection

• Grant number: 18/16214-3
• Support Opportunities: Scholarships in Brazil - Master
• Start date: December 01, 2018
• End date: February 29, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Zanoni Dias
• Grantee: Caroline Mazini Rodrigues
• 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

Abstract

Considering the occurrence of an event with high social impact, it is important to establish a space-time relation of available information and so, answer some questions about the event as "who", "how", "where" and "why". This work is part of the thematic FAPESP project "DéjàVu: Feature-Space-Time Coherence from Heterogeneous Data for Media Integrity Analytics and Interpretation of Events" and it proposes, from social network collected data, to determine the relevance of them for the analyzed event, allowing the correct construction of relationships among these data during an analysis phase later on. The main challenges of this work are the characteristics of the data which will be used: heterogeneity, as they come from different sources; multi-modality, such as texts, images and videos; unlabeled data, as they do not present label of straightforward relevance for the event; and unstructured data, as they do not possess characteristics which could be used directly during the learning. To determine the relevance of analyzed items, will be followed a sequence of phases which include: data preparation, in which we will eliminate redundancies and label some data; features engineering, in which we will extract visual and textual features; machine learning, in which we will analyze unsupervised and semi-supervised learning techniques; and validation and results analysis, in which we will evaluate the obtained solutions. (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)

RODRIGUES, CAROLINE MAZINI; SORIANO-VARGAS, AUREA; LAVI, BAHRAM; ROCHA, ANDERSON; DIAS, ZANONI. Manifold Learning for Real-World Event Understanding. IEEE Transactions on Information Forensics and Security, v. 16, p. 2957-2972, 2021. (18/16548-9, 18/16214-3, 17/16246-0, 15/11937-9, 18/05668-3, 13/08293-7, 17/12646-3, 17/16871-1)

PADILHA, RAFAEL; RODRIGUES, CAROLINE MAZINI; ANDALO, FERNANDA; BERTOCCO, GABRIEL; DIAS, ZANONI; ROCHA, ANDERSON. Forensic Event Analysis: From Seemingly Unrelated Data to Understanding. IEEE SECURITY & PRIVACY, v. 18, n. 6, p. 23-32, NOV 2020. (18/16214-3, 17/21957-2, 17/12646-3)

RODRIGUES, CAROLINE MAZINI; PEREIRA, LUIS; ROCHA, ANDERSON; DIAS, ZANONI; IEEE. Image Semantic Representation for Event Understanding. 2019 IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY (WIFS), v. N/A, p. 6-pg., 2019-01-01. (17/12646-3, 15/11937-9, 13/08293-7, 17/16246-0, 18/16548-9, 18/16214-3, 17/16871-1)

Academic Publications

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

RODRIGUES, Caroline Mazini. Image representativeness analysis for event description. 2020. Master's Dissertation - Universidade Estadual de Campinas (UNICAMP). Instituto de Computação Campinas, SP.