Image and Video Phylogeny Reconstruction

• Grant number: 13/05815-2
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: May 01, 2014
• End date: June 30, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Anderson de Rezende Rocha
• Grantee: Filipe de Oliveira Costa
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

In the last years, some researchers have successfully developed approaches for near-duplicate detection aiming at identifying the cohabiting versions of a given image or video online. However, only recently have there been the first attempts to go beyond the detection task and to find the structure of evolution within a set of related media overtime. In this work, our main objective is to design and develop approaches for identifying the structure of relationships of duplicates in a given set of semantically similar images or videos, and reconstructing a structure that represents their past history and ancestry information. For this, we aim at designing approaches that calculate the dissimilarities among images and videos and group them in distinct trees of processing history automatically. This project is linked to a larger project funded by the European Union denominated ``REWIND -- Reverse Engineering of Audio Visual Content Data'', in partnership with the european universities Politecnico di Milano (Italy), Università di Siena (Italy), Università degli Studi di Firenze (Italy), Imperial College (UK), Universidad de Vigo (Spain) and Fraunhofer IDMT (Germany).

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)

COSTA, FILIPE; OLIVEIRA, ALBERTO; FERRARA, PASQUALE; DIAS, ZANONI; GOLDENSTEIN, SIOME; ROCHA, ANDERSON. New dissimilarity measures for image phylogeny reconstruction. PATTERN ANALYSIS AND APPLICATIONS, v. 20, n. 4, p. 1289-1305, NOV 2017. (13/05815-2, 15/19222-9)

COSTA, FILIPE DE O.; LAMERI, SILVIA; BESTAGINI, PAOLO; DIAS, ZANONI; TUBARO, STEFANO; ROCHA, ANDERSON; IEEE. Hash-Based Frame Selection for Video Phylogeny. 2016 8TH IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY (WIFS 2016), v. N/A, p. 6-pg., 2016-01-01. (13/05815-2, 15/19222-9)

Academic Publications

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

COSTA, Filipe de Oliveira. Reconstrução de filogenias para imagens e vídeos. 2016. Doctoral Thesis - Universidade Estadual de Campinas (UNICAMP). Instituto de Computação Campinas, SP.