Details
| Original language | English |
|---|---|
| Title of host publication | MMSports'21: Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports |
| Editors | Rainer Lienhart, Thomas B. Moeslund, Hideo Saito |
| Publisher | Association for Computing Machinery (ACM) |
| Pages | 1-10 |
| Number of pages | 10 |
| ISBN (electronic) | 9781450386708 |
| ISBN (print) | 978-1-4503-8670-8 |
| Publication status | Published - 20 Oct 2021 |
Abstract
Keywords
- Datasets Event Detection, Events in Sports, Human Performance Analysis
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Engineering(all)
- Media Technology
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
MMSports'21: Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports. ed. / Rainer Lienhart; Thomas B. Moeslund; Hideo Saito. Association for Computing Machinery (ACM), 2021. p. 1-10.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games
AU - Biermann, Henrik
AU - Theiner, Jonas
AU - Bassek, Manuel
AU - Raabe, Dominik
AU - Memmert, Daniel
AU - Ewerth, Ralph
N1 - Funding Information: This project has received funding from the German Federal Ministry of Education and Research (BMBF – Bundesministerium für Bildung und Forschung) under 01IS20021A, 01IS20021B, and 01IS20021C. This research was supported by a grant from the German Research Council (DFG, Deutsche Forschungsgemeinschaft) to DM (grant ME 2678/30.1).
PY - 2021/10/20
Y1 - 2021/10/20
N2 - 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
AB - 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
KW - Datasets Event Detection
KW - Events in Sports
KW - Human Performance Analysis
UR - http://www.scopus.com/inward/record.url?scp=85119045626&partnerID=8YFLogxK
U2 - 10.1145/3475722.3482792
DO - 10.1145/3475722.3482792
M3 - Conference contribution
SN - 978-1-4503-8670-8
SP - 1
EP - 10
BT - MMSports'21: Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports
A2 - Lienhart, Rainer
A2 - Moeslund, Thomas B.
A2 - Saito, Hideo
PB - Association for Computing Machinery (ACM)
ER -