Carregant...
Carregant...

Vés al contingut (premeu Retorn)

SaltiNet: Scan-Path Prediction on 360 Degree Images Using Saliency Volumes

Autor
Assens, M.; Giro, X.; McGuinness, K.; O'Connor, N.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
The Second International Workshop on Egocentric Perception, Interaction and Computing
Any de l'edició
2018
Data de presentació
2017-10-29
Llibre d'actes
2017 IEEE International Conference on Computer Vision Workshops: ICCVW 2017: 22-29 October 2017, Venice, Italy: proceedings
Pàgina inicial
2331
Pàgina final
2338
Editor
IEEE Press
DOI
https://doi.org/10.1109/ICCVW.2017.275 Obrir en finestra nova
Projecte finançador
Procesado de información heterogénea y señales en grafos para Big Data:aplicación en cribado de alto rendimiento,teledetección,multimedia y HCI
Procesado de señales multimodales y aprendizaje automático en grafos.
Repositori
http://hdl.handle.net/2117/114891 Obrir en finestra nova
https://arxiv.org/abs/1707.03123 Obrir en finestra nova
URL
http://ieeexplore.ieee.org/document/8265485/ Obrir en finestra nova
Resum
We introduce SaltiNet, a deep neural network for scan-path prediction trained on 360-degree images. The model 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 computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency volumes. Sampling strategies over these volumes are used to genera...
Citació
Assens, M., Giro, X., McGuinness, K., O'Connor, N. SaltiNet: scan-path prediction on 360 degree images using saliency volumes. A: International Workshop on Egocentric Perception, Interaction and Computing. "2017 IEEE International Conference on Computer Vision Workshops (ICCVW)". IEEE Press, 23/01/2018, p. 2331-2338.
Paraules clau
Backpropagation, Computer vision, Cross entropy, Deep neural networks, Sampling strategies, Scan path, Source codes
Grup de recerca
GPI - Grup de Processament d'Imatge i Vídeo
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

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