Mastering Scene Understanding: Scene Graphs to the Rescue

  • Carlos Caetano UNICAMP
  • Leo Sampaio Ferraz Ribeiro UNICAMP
  • Camila Laranjeira UFMG
  • Gabriel Oliveira dos Santos UNICAMP
  • Artur Barros UNICAMP
  • Caio Petrucci UNICAMP
  • Andreza Aparecida dos Santos UNICAMP
  • João Macedo UFMG
  • Gil Carvalho UNICAMP
  • Fabricio Benevenuto UFMG
  • Jefersson A. dos Santos University of Sheffield
  • Sandra Avila UNICAMP

Resumo


The evolution of scene understanding in computer vision has seen remarkable advancements, driven significantly by the development and utilization of scene graphs due to their powerful structural and semantic representation. This structured approach allows for better contextual understanding, facilitating tasks such as image captioning, image generation, image retrieval, human-object interaction, and visual question answering. This tutorial paper aims to comprehensively investigate the current scene graph research by discussing their generation methods, applications, standard datasets, and future development insights.
Palavras-chave: Visualization, Computer vision, Image synthesis, Semantics, Image retrieval, Tutorials, Question answering (information retrieval), Standards
Publicado
30/09/2024
Como Citar

Selecione um Formato
CAETANO, Carlos et al. Mastering Scene Understanding: Scene Graphs to the Rescue. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 37. , 2024, Manaus/AM. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2024 .