Event Room, Technopole , via Vivarelli, 2, 41125 Modena
Dr. Iuri Frosio , PhD, NVIDIA USA
Working in a company that is leader in both the videogames and machine learning fields offers exciting research opportunities at the intersection between these two domains. In this talk, I will illustrate two of these applications In the first part, I will concentrate my attention on saliency prediction in videogames, based on a dataset of Fortnite sequences that we acquired in 2019 I will illustrate the peculiar aspects of saliency in videogames, show that different frames in video sequences are not equally reliable, depending on the number of observers and frame content, and propose a general paradigm that explicitly takes this aspect into account when training a deep learning saliency prediction model.
In the second part of the talk, I will introduce the problem of cheating in videogames and propose a deep learning based solution for the case of visual cheating Our method allows identifying cheaters with high probability, and it is designed to be robust with respect to potential adversarial attacks put in place by cheat designers I will conclude the talk by illustrating other potential research areas including videogames and deep learning