TY - GEN
T1 - 6MapNet
T2 - 8th International Workshop on Machine Learning and Data Mining for Sports Analytics, MLSA 2021, colocated with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery, ECML PKDD 2021
AU - Kim, Hyunsung
AU - Kim, Jihun
AU - Chung, Dongwook
AU - Lee, Jonghyun
AU - Yoon, Jinsung
AU - Ko, Sang Ki
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Playing Style Representation
KW - Siamese Neural Network
KW - Spatiotemporal Tracking Data
KW - Sports Analytics
KW - Triplet Loss
UR - https://www.scopus.com/pages/publications/85130247026
U2 - 10.1007/978-3-031-02044-5_1
DO - 10.1007/978-3-031-02044-5_1
M3 - Conference contribution
AN - SCOPUS:85130247026
SN - 9783031020438
T3 - Communications in Computer and Information Science
SP - 3
EP - 14
BT - Machine Learning and Data Mining for Sports Analytics - 8th International Workshop, MLSA 2021, Revised Selected Papers
A2 - Brefeld, Ulf
A2 - Davis, Jesse
A2 - Van Haaren, Jan
A2 - Zimmermann, Albrecht
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 13 September 2021 through 13 September 2021
ER -