@article{16194,
  keywords = {classification, Detection, soccer events, spotting, 3d CNN},
  author = {Olav Rongved and Steven Hicks and Vajira Thambawita and H{\r a}kon Stensland and Evi Zouganeli and Dag Johansen and Cise Midoglu and Michael Riegler and P{\r a}l Halvorsen},
  title = {Using 3D Convolutional Neural Networks for Real-time Detection of Soccer Events},
  abstract = {Developing systems for the automatic detection of events in video is a task which has gained attention in many areas including sports. More specifically, event detection for soccer videos has been studied widely in the literature. However, there are still a number of shortcomings in the state-of-the-art such as high latency, making it challenging to operate at the live edge. In this paper, we present an algorithm to detect events in soccer videos in real time, using 3D convolutional neural networks. We test our algorithm on three different datasets from SoccerNet, the Swedish Allsvenskan, and the Norwegian Eliteserien. Overall, the results show that we can detect events with high recall, low latency, and accurate time estimation. The trade-off is a slightly lower precision compared to the current state-of-the-art, which has higher latency and performs better when a less accurate time estimation can be accepted. In addition to the presented algorithm, we perform an extensive ablation study on how the different parts of the training pipeline affect the final results.},
  year = {2021},
  journal = {International Journal of Semantic Computing},
  volume = {15},
  number = {2},
  pages = {161 - 187},
  month = {Jan-06-2021},
  publisher = {World Scientific},
  issn = {1793-351X},
  url = {https://www.worldscientific.com/doi/abs/10.1142/S1793351X2140002X},
  doi = {10.1142/S1793351X2140002X},
}