A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games

TL;DR

This paper introduces a comprehensive taxonomy and multimodal dataset for detecting a wide range of events in invasion sports, addressing previous limitations of ambiguous definitions and dataset quality, and demonstrating the robustness of the approach.

Contribution

It provides a universal taxonomy for invasion game events and releases annotated multimodal datasets, enabling more consistent and detailed event detection research.

Findings

Taxonomy covers low and high-level events in invasion sports.

Datasets include video and positional data with gold-standard annotations.

Event annotation ambiguity increases with event complexity.

Abstract

The automatic detection of events in complex sports games like soccer and handball using positional or video data is of large interest in research and industry. One requirement is a fundamental understanding of underlying concepts, i.e., events that occur on the pitch. Previous work often deals only with so-called low-level events based on well-defined rules such as free kicks, free throws, or goals. High-level events, such as passes, are less frequently approached due to a lack of consistent definitions. This introduces a level of ambiguity that necessities careful validation when regarding event annotations. Yet, this validation step is usually neglected as the majority of studies adopt annotations from commercial providers on private datasets of unknown quality and focuses on soccer only. To address these issues, we present (1) a universal taxonomy that covers a wide range of low and high-level events for invasion games and is exemplarily refined to soccer and handball, and (2) release two multi-modal datasets comprising video and positional data with gold-standard annotations to foster research in fine-grained and ball-centered event spotting. Experiments on human performance demonstrate the robustness of the proposed taxonomy, and that disagreements and ambiguities in the annotation increase with the complexity of the event. An I3D model for video classification is adopted for event spotting and reveals the potential for benchmarking. Datasets are available at: https://github.com/mm4spa/eigd