Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Demonstration of an open source framework for qualitative evaluation of CBIR systems

Autor
Gomez, P.; Mohedano, E.; McGuinness, K.; Giro, X.; O'Connor, N.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
ACM Multimedia Conference 2018
Any de l'edició
2018
Data de presentació
2018-10-24
Llibre d'actes
Proceedings of 2018 ACM Multimedia Conference, Seoul, Republic of Korea, October 22-26, 2018 (MM’18)
Pàgina inicial
1256
Pàgina final
1257
DOI
https://doi.org/10.1145/3240508.3241395 Obrir en finestra nova
Projecte finançador
Procesado de señales multimodales y aprendizaje automático en grafos.
Repositori
http://hdl.handle.net/2117/123448 Obrir en finestra nova
https://imatge.upc.edu/web/publications/demonstration-open-source-framework-qualitative-evaluation-cbir-systems Obrir en finestra nova
URL
https://dl.acm.org/citation.cfm?id=3241395 Obrir en finestra nova
Resum
Evaluating image retrieval systems in a quantitative way, for example by computing measures like mean average precision, allows for objective comparisons with a ground-truth. However, in cases where ground-truth is not available, the only alternative is to collect feedback from a user. Thus, qualitative assessments become important to better understand how the system works. Visualizing the results could be, in some scenarios, the only way to evaluate the results obtained and also the only opport...
Paraules clau
content-based image retrieval, deep learning, open source, retrieval, user interface, visual search
Grup de recerca
GPI - Grup de Processament d'Imatge i Vídeo
IDEAI-UPC Intelligent Data Science and Artificial Intelligence

Participants

  • Gomez Duran, Paula  (autor ponent)
  • Mohedano, Eva  (autor ponent)
  • McGuinness, Kevin  (autor ponent)
  • Giro Nieto, Xavier  (autor ponent)
  • O'Connor, Noel  (autor ponent)