Predicting Soccer Penalty Kick Direction Using Human Action Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Freire-Obregón, David, Santana, Oliverio J., Lorenzo-Navarro, Javier, Hernández-Sosa, Daniel, Castrillón-Santana, Modesto
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913945726484480
author Freire-Obregón, David
Santana, Oliverio J.
Lorenzo-Navarro, Javier
Hernández-Sosa, Daniel
Castrillón-Santana, Modesto
author_facet Freire-Obregón, David
Santana, Oliverio J.
Lorenzo-Navarro, Javier
Hernández-Sosa, Daniel
Castrillón-Santana, Modesto
contents Action anticipation has become a prominent topic in Human Action Recognition (HAR). However, its application to real-world sports scenarios remains limited by the availability of suitable annotated datasets. This work presents a novel dataset of manually annotated soccer penalty kicks to predict shot direction based on pre-kick player movements. We propose a deep learning classifier to benchmark this dataset that integrates HAR-based feature embeddings with contextual metadata. We evaluate twenty-two backbone models across seven architecture families (MViTv2, MViTv1, SlowFast, Slow, X3D, I3D, C2D), achieving up to 63.9% accuracy in predicting shot direction (left or right), outperforming the real goalkeepers' decisions. These results demonstrate the dataset's value for anticipatory action recognition and validate our model's potential as a generalizable approach for sports-based predictive tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12617
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Predicting Soccer Penalty Kick Direction Using Human Action Recognition
Freire-Obregón, David
Santana, Oliverio J.
Lorenzo-Navarro, Javier
Hernández-Sosa, Daniel
Castrillón-Santana, Modesto
Computer Vision and Pattern Recognition
Action anticipation has become a prominent topic in Human Action Recognition (HAR). However, its application to real-world sports scenarios remains limited by the availability of suitable annotated datasets. This work presents a novel dataset of manually annotated soccer penalty kicks to predict shot direction based on pre-kick player movements. We propose a deep learning classifier to benchmark this dataset that integrates HAR-based feature embeddings with contextual metadata. We evaluate twenty-two backbone models across seven architecture families (MViTv2, MViTv1, SlowFast, Slow, X3D, I3D, C2D), achieving up to 63.9% accuracy in predicting shot direction (left or right), outperforming the real goalkeepers' decisions. These results demonstrate the dataset's value for anticipatory action recognition and validate our model's potential as a generalizable approach for sports-based predictive tasks.
title Predicting Soccer Penalty Kick Direction Using Human Action Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.12617