Advanced search
Start date
Betweenand
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Contextual movement models based on normalizing flows

Full text
Author(s):
Fadel, Samuel G. [1] ; Mair, Sebastian [2] ; da Silva Torres, Ricardo [3] ; Brefeld, Ulf [2]
Total Authors: 4
Affiliation:
[1] Univ Estadual Campinas, Campinas, SP - Brazil
[2] Leuphana Univ Luneburg, Luneburg - Germany
[3] Norwegian Univ Sci & Technol, Alesund - Norway
Total Affiliations: 3
Document type: Journal article
Source: AStA-Advances in Statistical Analysis; AUG 2021.
Web of Science Citations: 0
Abstract

Movement models predict positions of players (or objects in general) over time and are thus key to analyzing spatiotemporal data as it is often used in sports analytics. Existing movement models are either designed from physical principles or are entirely data-driven. However, the former suffers from oversimplifications to achieve feasible and interpretable models, while the latter relies on computationally costly, from a current point of view, nonparametric density estimations and require maintaining multiple estimators, each responsible for different types of movements (e.g., such as different velocities). In this paper, we propose a unified contextual probabilistic movement model based on normalizing flows. Our approach learns the desired densities by directly optimizing the likelihood and maintains only a single contextual model that can be conditioned on auxiliary variables. Training is simultaneously performed on all observed types of movements, resulting in an effective and efficient movement model. We empirically evaluate our approach on spatiotemporal data from professional soccer. Our findings show that our approach outperforms the state of the art while being orders of magnitude more efficient with respect to computation time and memory requirements. (AU)

FAPESP's process: 17/24005-2 - Temporal relational reasoning with neural networks
Grantee:Samuel Gomes Fadel
Support type: Scholarships in Brazil - Doctorate
FAPESP's process: 16/50250-1 - The secret of playing football: Brazil versus the Netherlands
Grantee:Sergio Augusto Cunha
Support type: Research Projects - Thematic Grants
FAPESP's process: 15/24494-8 - Communications and processing of big data in cloud and fog computing
Grantee:Nelson Luis Saldanha da Fonseca
Support type: Research Projects - Thematic Grants
FAPESP's process: 17/20945-0 - Multi-user equipment approved in great 16/50250-1: local positioning system
Grantee:Sergio Augusto Cunha
Support type: Multi-user Equipment Program
FAPESP's process: 18/19350-5 - Neural networks for temporal relational reasoning in soccer analysis
Grantee:Samuel Gomes Fadel
Support type: Scholarships abroad - Research Internship - Doctorate
FAPESP's process: 19/17729-0 - Data-driven approaches for soccer match analysis: an e-Science perspective
Grantee:Paulo Roberto Pereira Santiago
Support type: Regular Research Grants