Loading...
Loading...

Go to the content (press return)

PathGAN: visual scanpath prediction with generative adversarial networks

Author
Assens, M.; Giro, X.; McGuinness, K.; O'Connor, N.
Type of activity
Presentation of work at congresses
Name of edition
Third International Workshop on Egocentric Perception, Interaction and Computing
Date of publication
2018
Presentation's date
2018-09-09
Book of congress proceedings
Computer Vision: ECCV 2018 Workshops, Munich, Germany, September 8-14, 2018: proceedings, part V
First page
406
Last page
422
Publisher
Springer
DOI
10.1007/978-3-030-11021-5_25
Project funding
Multimodal Signal Processing and Machine Learning on Graphs
Repository
http://hdl.handle.net/2117/130229 Open in new window
https://imatge-upc.github.io/pathgan/ Open in new window
URL
https://link.springer.com/chapter/10.1007%2F978-3-030-11021-5_25 Open in new window
Abstract
We introduce PathGAN, a deep neural network for visual scanpath prediction trained on adversarial examples. A visual scanpath is defined as the sequence of fixation points over an image defined by a human observer with its gaze. PathGAN is composed of two parts, the generator and the discriminator. Both parts extract features from images using off-the-shelf networks, and train recurrent layers to generate or discriminate scanpaths accordingly. In scanpath prediction, the stochastic nature of the...
Citation
Assens, M. [et al.]. PathGAN: visual scanpath prediction with generative adversarial networks. A: Workshop on Egocentric Perception, Interaction and Computing. "Computer Vision: ECCV 2018 Workshops, Munich, Germany, September 8-14, 2018: proceedings, part V". Berlín: Springer, 2019, p. 406-422.
Keywords
GAN, adversarial training, cGAN, saliency, scanpath
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 )