Loading...
Loading...

Go to the content (press return)

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

Author
Assens, M.; Giro, X.; McGuinness, K.; O'Connor, N.
Type of activity
Presentation of work at congresses
Name of edition
The Second International Workshop on Egocentric Perception, Interaction and Computing
Date of publication
2018
Presentation's date
2017-10-29
Book of congress proceedings
2017 IEEE International Conference on Computer Vision Workshops: ICCVW 2017: 22-29 October 2017, Venice, Italy: proceedings
First page
2331
Last page
2338
Publisher
IEEE Press
DOI
https://doi.org/10.1109/ICCVW.2017.275 Open in new window
Project funding
Heterogeneous information and graph signal processing for the Big Data era. Application to high-throughput, remote sensing, multimedia and human computer interfaces
Multimodal Signal Processing and Machine Learning on Graphs
Repository
http://hdl.handle.net/2117/114891 Open in new window
https://arxiv.org/abs/1707.03123 Open in new window
URL
http://ieeexplore.ieee.org/document/8265485/ Open in new window
Abstract
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...
Citation
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.
Keywords
Backpropagation, Computer vision, Cross entropy, Deep neural networks, Sampling strategies, Scan path, Source codes
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

  • Assens, Marc  (author and speaker )
  • Giro Nieto, Xavier  (author and speaker )
  • McGuinness, Kevin  (author and speaker )
  • O'Connor, Noel  (author and speaker )