Investigating the Performance of Optimization Techniques on Deep Learning Models to Identify Dota2 Game Events

Matheus Faria, Etienne Julia, Henrique Fernandes, Marcelo Zanchetta do Nascimento, Rita Julia

2023

Abstract

Game logs are an important part of the player experience analysis in literature. They describe the major actions and events (related to the players or other elements) that affect the progress of a game. In most existing games (especially popular commercial games like FIFA, Dota2 and Valorant), their access is typically restricted to the game’s developers. Deep Learning (DL) approaches have been proposed to perform game event classification from videos. However, retrieving relevant information about these game events (normally associated with actions performed by players) in real-time is still a challenge. Existing approaches require high computational power that serves as an additional issue. In this sense, the present paper investigates a set of approaches that aim to reduce the computational cost of DL-based models - more specifically, Convolutional Neural Networks (CNN) based on Residual Nets architectures - through Genetic Algorithm and Bayesian Optimization. This investigation is carried out in the context of Dota2 game event classification. The comparative analysis showed that the models obtained herein achieved a classification performance as good as the models of the state-ofthe-art considering the Dota2 dataset, but with significantly fewer parameters. Thus, this work can help in the generation of optimized CNNs for real-time applications.

Download


Paper Citation


in Harvard Style

Faria M., Julia E., Fernandes H., Zanchetta do Nascimento M. and Julia R. (2023). Investigating the Performance of Optimization Techniques on Deep Learning Models to Identify Dota2 Game Events. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 881-888. DOI: 10.5220/0011691800003417


in Bibtex Style

@conference{visapp23,
author={Matheus Faria and Etienne Julia and Henrique Fernandes and Marcelo Zanchetta do Nascimento and Rita Julia},
title={Investigating the Performance of Optimization Techniques on Deep Learning Models to Identify Dota2 Game Events},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={881-888},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011691800003417},
isbn={978-989-758-634-7},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - Investigating the Performance of Optimization Techniques on Deep Learning Models to Identify Dota2 Game Events
SN - 978-989-758-634-7
AU - Faria M.
AU - Julia E.
AU - Fernandes H.
AU - Zanchetta do Nascimento M.
AU - Julia R.
PY - 2023
SP - 881
EP - 888
DO - 10.5220/0011691800003417
PB - SciTePress