Summary of Classification Of Tennis Actions Using Deep Learning, by Emil Hovad (1 and 2) et al.
Classification of Tennis Actions Using Deep Learning
by Emil Hovad, Therese Hougaard-Jensen, Line Katrine Harder Clemmensen
First submitted to arxiv on: 4 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper explores the application of deep learning techniques to classify tennis actions with high precision, which is crucial for automatic game statistics collection, replaying specific actions for strategy or player improvement. The authors train three SlowFast-based models on the THETIS dataset and achieve a generalization accuracy of 74%, demonstrating good performance in tennis action classification. They also provide an error analysis and highlight directions for improving tennis datasets. Furthermore, they discuss the limitations of the current publicly available tennis datasets and outline future steps to advance this area. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using special computer algorithms called deep learning to recognize specific events in videos. For sports like tennis, this can help us collect game statistics automatically or replay interesting actions for strategy or player improvement. The authors test these algorithms on a large dataset of tennis actions and find that they work pretty well, with an accuracy of 74%. They also explain why some actions were misclassified and suggest ways to make the data better. |
Keywords
* Artificial intelligence * Classification * Deep learning * Generalization * Precision
