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

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 generate scan-paths over the 360-degree images. Our experiments show the advantages of using saliency volumes, and how they can be used for related tasks. Our source code and trained models available at https://github.com/massens/saliency-360salient-2017.

Cite

Text

Assens et al. "SaltiNet: Scan-Path Prediction on 360 Degree Images Using Saliency Volumes." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.275

Markdown

[Assens et al. "SaltiNet: Scan-Path Prediction on 360 Degree Images Using Saliency Volumes." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/assens2017iccvw-saltinet/) doi:10.1109/ICCVW.2017.275

BibTeX

@inproceedings{assens2017iccvw-saltinet,
  title     = {{SaltiNet: Scan-Path Prediction on 360 Degree Images Using Saliency Volumes}},
  author    = {Assens, Marc and Giró-i-Nieto, Xavier and McGuinness, Kevin and O'Connor, Noel E.},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2017},
  pages     = {2331-2338},
  doi       = {10.1109/ICCVW.2017.275},
  url       = {https://mlanthology.org/iccvw/2017/assens2017iccvw-saltinet/}
}