activity
20182021
most citedConvolutional Neural Networks Deceived by Visual Illusions

5 citations · 9 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG2021★ 2 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.CV2019★ 2 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★ 5 cited

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…