{"ID":2894125,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.12617","arxiv_id":"2507.12617","title":"Predicting Soccer Penalty Kick Direction Using Human Action Recognition","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2507.12617","url_pdf":"https://arxiv.org/pdf/2507.12617v1","authors":"[\"David Freire-Obregón\",\"Oliverio J. Santana\",\"Javier Lorenzo-Navarro\",\"Daniel Hernández-Sosa\",\"Modesto Castrillón-Santana\"]","published":"2025-07-16T20:27:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}