4 code implementations • 17 Aug 2022 • Gabriel Van Zandycke, Vladimir Somers, Maxime Istasse, Carlo Del Don, Davide Zambrano
With the recent development of Deep Learning applied to Computer Vision, sport video understanding has gained a lot of attention, providing much richer information for both sport consumers and leagues.
1 code implementation • 1 Dec 2021 • Seyed Abolfazl Ghasemzadeh, Gabriel Van Zandycke, Maxime Istasse, Niels Sayez, Amirafshar Moshtaghpour, Christophe De Vleeschouwer
In addition to the increased complexity resulting from the multiplication of single-task models, the use of the off-the-shelf models also impedes the performance due to the complexity and specificity of the team sports scenes, such as strong occlusion and motion blur.
1 code implementation • 3 Sep 2021 • Adrien Deliège, Maxime Istasse, Ashwani Kumar, Christophe De Vleeschouwer, Marc Van Droogenbroeck
More importantly, they also demonstrate that ordinal pooling leads to consistent improvements in the accuracy over average- or max-pooling operations while speeding up the training and alleviating the issue of the choice of the pooling operations and activation functions to be used in the networks.
1 code implementation • ICLR Workshop Rethinking_ML_Papers 2021 • Maxime Istasse, Kim Mens, Christophe De Vleeschouwer
But this is not the case for output mathematics.
no code implementations • 1 Jul 2019 • Maxime Istasse, Julien Moreau, Christophe De Vleeschouwer
Assigning team labels to players in a sport game is not a trivial task when no prior is known about the visual appearance of each team.