FACTS: Fine-Grained Action Classification for Tactical Sports

TL;DR

FACTS is a transformer-based model that directly classifies fine-grained actions in tactical sports from raw video, achieving state-of-the-art accuracy without pose estimation or sensors, and introduces a new fencing dataset.

Contribution

The paper presents FACTS, a novel transformer approach for fine-grained action recognition in sports, and provides a new detailed fencing dataset, advancing sports analytics.

Findings

Achieved 90% accuracy on fencing actions

Achieved 83.25% accuracy on boxing actions

Introduced a new fencing action dataset

Abstract

Classifying fine-grained actions in fast-paced, close-combat sports such as fencing and boxing presents unique challenges due to the complexity, speed, and nuance of movements. Traditional methods reliant on pose estimation or fancy sensor data often struggle to capture these dynamics accurately. We introduce FACTS, a novel transformer-based approach for fine-grained action recognition that processes raw video data directly, eliminating the need for pose estimation and the use of cumbersome body markers and sensors. FACTS achieves state-of-the-art performance, with 90% accuracy on fencing actions and 83.25% on boxing actions. Additionally, we present a new publicly available dataset featuring 8 detailed fencing actions, addressing critical gaps in sports analytics resources. Our findings enhance training, performance analysis, and spectator engagement, setting a new benchmark for action classification in tactical sports.