Título:
|
PathGAN: visual scanpath prediction with generative adversarial networks
|
Autor/a:
|
Assens, Marc; Giró Nieto, Xavier; McGuinness, Kevin; O'Connor, Noel
|
Otros autores:
|
Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions; Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo |
Abstract:
|
“This is a post-peer-review, pre-copyedit version of an article published in: Computer Vision – ECCV 2018 Workshops. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-030-11021-5_25”. |
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 data makes it very difficult to generate realistic predictions using supervised learning strategies, but we adopt adversarial training as a suitable alternative. Our experiments prove how PathGAN improves the state of the art of visual scanpath prediction on the iSUN and Salient360! datasets. |
Abstract:
|
Peer Reviewed |
Materia(s):
|
-Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo -Neural networks (Computer science) -Image processing--Digital techniques -Computer vision -saliency -scanpath -adversarial training -GAN -cGAN -Xarxes neuronals (Informàtica) -Imatges -- Processament -- Tècniques digitals -Visió per ordinador |
Derechos:
|
|
Tipo de documento:
|
Artículo - Versión presentada Objeto de conferencia |
Editor:
|
Springer
|
Compartir:
|
|