What Are You Looking At? Team Fight Prediction Through Player Camera

TY - GEN

T1 - What Are You Looking At? Team Fight Prediction Through Player Camera

AU - Tot, Marko

AU - Conserva, Michelangelo

AU - Chitayat, Alan Pedrassoli

AU - Kokkinakis, Athanasios

AU - Patra, Sagarika

AU - Demediuk, Simon

AU - Munoz, Alvaro Caceres

AU - Olarewaju, Oluseji

AU - Ursu, Marian

AU - Kirmann, Ben

AU - Hook, Jonathan

AU - Block, Florian

AU - Drachen, Anders

AU - Perez-Liebana, Diego

N1 - Funding Information: This paper is part-funded by EPSRC CDT in Intelligent Games and Game Intelligence (lOGI) EP/LOl5846/1 and the Audience of the Future program by UK Research and Innovation through the Industrial Strategy Challenge Fund (grant no.I04775) as part of the Weavr project (weavr.tv). Publisher Copyright: © 2021 IEEE.

PY - 2021/12/7

Y1 - 2021/12/7

N2 - Esport is a large and still growing industry with vast audiences. Multiplayer Online Battle Arenas (MOBAs), a sub-genre of esports, possess a very complex environment, which often leads to experts missing important coverage while broadcasting live competitions. One common game event that holds significant importance for broadcasting is referred to as a team fight engagement. Professional player's own knowledge and understanding of the game may provide a solution to this problem. This paper suggests a model that predicts and detects ongoing team fights in a live scenario. This approach outlines a novel technique of deriving representations of a complex game environment by relying on player knowledge. This is done by analysing the positions of the in-game characters and their associated cameras, utilising this data to train a neural network. The proposed model is able to both assist in the production of live esport coverage as well as provide a live, expert-derived, analysis of the game without the need of relying on outside sources.

AB - Esport is a large and still growing industry with vast audiences. Multiplayer Online Battle Arenas (MOBAs), a sub-genre of esports, possess a very complex environment, which often leads to experts missing important coverage while broadcasting live competitions. One common game event that holds significant importance for broadcasting is referred to as a team fight engagement. Professional player's own knowledge and understanding of the game may provide a solution to this problem. This paper suggests a model that predicts and detects ongoing team fights in a live scenario. This approach outlines a novel technique of deriving representations of a complex game environment by relying on player knowledge. This is done by analysing the positions of the in-game characters and their associated cameras, utilising this data to train a neural network. The proposed model is able to both assist in the production of live esport coverage as well as provide a live, expert-derived, analysis of the game without the need of relying on outside sources.

KW - engagement

KW - esports

KW - MOBA

KW - neural network

KW - player analytics

KW - team fight

UR - http://www.scopus.com/inward/record.url?scp=85122946848&partnerID=8YFLogxK

U2 - 10.1109/CoG52621.2021.9619038

DO - 10.1109/CoG52621.2021.9619038

M3 - Conference contribution

AN - SCOPUS:85122946848

T3 - IEEE Conference on Computatonal Intelligence and Games, CIG

BT - 2021 IEEE Conference on Games, CoG 2021

PB - IEEE Computer Society

T2 - 2021 IEEE Conference on Games, CoG 2021

Y2 - 17 August 2021 through 20 August 2021

ER -