Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Scanpath and saliency prediction on 360 degree images

Autor
Assens, M.; Giro, X.; McGuinness, K.; O'Connor, N.
Tipus d'activitat
Article en revista
Revista
Signal processing: image communication
Data de publicació
2018-06-23
Volum
69
Pàgina inicial
8
Pàgina final
14
DOI
https://doi.org/10.1016/j.image.2018.06.006 Obrir en finestra nova
Projecte finançador
Procesado de señales multimodales y aprendizaje automático en grafos.
Repositori
http://hdl.handle.net/2117/119346 Obrir en finestra nova
https://imatge.upc.edu/web/publications/scanpath-and-saliency-prediction-360-degree-images Obrir en finestra nova
URL
https://www.sciencedirect.com/science/article/pii/S0923596518306209 Obrir en finestra nova
Resum
We introduce deep neural networks for scanpath and saliency prediction trained on 360-degree images. The scanpath prediction model called SaltiNet is based on a temporal-aware novel representation of saliency information named the saliency volume. The first part of the network consists of a model trained to generate saliency volumes, whose parameters are fit by back-propagation using a binary cross entropy (BCE) loss over downsampled versions of the saliency volumes. Sampling strategies over the...
Citació
Assens, M., Giro, X., McGuinness, K., O'Connor, N. Scanpath and saliency prediction on 360 degree images. "Signal processing: image communication", 23 Juny 2018, vol. 69, p. 8-14.
Paraules clau
deep learning, machine learning, saliency, scanpath, visual attention
Grup de recerca
GPI - Grup de Processament d'Imatge i Vídeo
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

  • Assens Reina, Marc  (autor)
  • Giro Nieto, Xavier  (autor)
  • McGuinness, Kevin  (autor)
  • O'Connor, Noel  (autor)