Subjectivity as multi-video summarization coverage criteria

• Grant number: 24/16875-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2024
• End date: October 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Rudinei Goularte
• Grantee: Kaylaine Bessa da Silva
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

This project aims to investigate the use of subjectivity as a coverage criterion for multi-video summary generation in the video news domain. Multi-video summarization is an actual and challenging research topic in which the main difficulty is the development of content selection criteria allowing the choice of proper video segments to compose the final video summary among a set of videos about the same subject. Related works have used Subjectivity as an exclusion criterion, filtering out segments classified as subjective. However, those subjective segments may contain supplementary information, enriching the facts reported to the user. This information complementarity corresponds to the Coverage criterion. To the best of the acquired knowledge, this approach was not yet explored.