activity
20182021
most citedSynthesizing Visual Illusions Using Generative Adversarial Networks

2 citations · 4 across the 3 of their papers we have counts for

collaborators

6 papers

cs.LG20212 cited

Learning Football Body-Orientation as a Matter of Classification

Adrià Arbués-Sangüesa, Adrián Martín, Paulino Granero +2

Orientation is a crucial skill for football players that becomes a differential factor in a large set of events, especially the ones involving passes. However, existing orientation…

cs.CV2020

Using Player's Body-Orientation to Model Pass Feasibility in Soccer

Adrià Arbués-Sangüesa, Adrián Martín, Javier Fernández +2

Given a monocular video of a soccer match, this paper presents a computational model to estimate the most feasible pass at any given time. The method leverages offensive player's o…

cs.CV2020

Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players

Adrià Arbués-Sangüesa, Adrián Martín, Javier Fernández +3

Although orientation has proven to be a key skill of soccer players in order to succeed in a broad spectrum of plays, body orientation is a yet-little-explored area in sports analy…

cs.CV2019

Visual Illusions Also Deceive Convolutional Neural Networks: Analysis and Implications

A. Gomez-Villa, A. Martín, J. Vazquez-Corral +2

Visual illusions allow researchers to devise and test new models of visual perception. Here we show that artificial neural networks trained for basic visual tasks in natural images…

cs.CV20192 cited

Synthesizing Visual Illusions Using Generative Adversarial Networks

Alexander Gomez-Villa, Adrian Martín, Javier Vazquez-Corral +2

Visual illusions are a very useful tool for vision scientists, because they allow them to better probe the limits, thresholds and errors of the visual system. In this work we intro…

cs.CV2018

Convolutional Neural Networks Deceived by Visual Illusions

Alexander Gomez-Villa, Adrián Martín, Javier Vazquez-Corral +1

Visual illusions teach us that what we see is not always what it is represented in the physical world. Its special nature make them a fascinating tool to test and validate any new…