AuthorsM. Lux, M. Riegler, D. Dang-Nguyen, J. Pirker, M. Potthast and P. Halvorsen
TitleGameStory Task at MediaEval 2019
AfilliationCommunication Systems, Machine Learning
Project(s)Department of Holistic Systems
StatusPublished
Publication TypeProceedings, refereed
Year of Publication2019
Conference NameProceedings of MediaEval 2019
Date Published10/2019
PublisherCEUR Workshop Proceedings (CEUR-WS.org)
Abstract

Game video streams are watched by millions, so that, meanwhile, one can make a living from broadcasting and commenting video games, whereas some have become professional e-sports athletes. E-sports leagues and tournaments have emerged worldwide, where players compete in controlled environments, streaming the matches online, and allowing the audience to discuss and criticize the game- play. In the GameStory task, held for the second time at MediaEval, we foster research into this exciting domain. Our focus is on an- alyzing and summarizing video game streams. With the help of ZNIPE.tv, we compiled a high-quality dataset of a Counter-Strike: Global Offensive tournament alongside ground truth labels for two analysis tasks, forming a basis for summarization.

Citation Key27106

Contact person