6MapNet: Representing Soccer Players from Tracking Data by a Triplet Network

Hyunsung Kim, Jihun Kim, Dongwook Chung, Jonghyun Lee, Jinsung Yoon, Sang Ki Ko

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Although the values of individual soccer players have become astronomical, subjective judgments still play a big part in the player analysis. Recently, there have been new attempts to quantitatively grasp players’ styles using video-based event stream data. However, they have some limitations in scalability due to high annotation costs and sparsity of event stream data. In this paper, we build a triplet network named 6MapNet that can effectively capture the movement styles of players using in-game GPS data. Without any annotation of soccer-specific actions, we use players’ locations and velocities to generate two types of heatmaps. Our subnetworks then map these heatmap pairs into feature vectors whose similarity corresponds to the actual similarity of playing styles. The experimental results show that players can be accurately identified with only a small number of matches by our method.

Original languageEnglish
Title of host publicationMachine Learning and Data Mining for Sports Analytics - 8th International Workshop, MLSA 2021, Revised Selected Papers
EditorsUlf Brefeld, Jesse Davis, Jan Van Haaren, Albrecht Zimmermann
PublisherSpringer Science and Business Media Deutschland GmbH
Pages3-14
Number of pages12
ISBN (Print)9783031020438
DOIs
StatePublished - 2022
Event8th International Workshop on Machine Learning and Data Mining for Sports Analytics, MLSA 2021 - Virtual, Online
Duration: 13 Sep 202113 Sep 2021

Publication series

NameCommunications in Computer and Information Science
Volume1571 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference8th International Workshop on Machine Learning and Data Mining for Sports Analytics, MLSA 2021
CityVirtual, Online
Period13/09/2113/09/21

Keywords

  • Playing Style Representation
  • Siamese Neural Network
  • Spatiotemporal Tracking Data
  • Sports Analytics
  • Triplet Loss

Fingerprint

Dive into the research topics of '6MapNet: Representing Soccer Players from Tracking Data by a Triplet Network'. Together they form a unique fingerprint.

Cite this