@misc{15910, author = {Olav Rongved and Steven Hicks and Vajira Thambawita and H{\r a}kon Stensland and Evi Zouganeli and Dag Johansen and Michael Riegler and P{\r a}l Halvorsen}, title = {Real-Time Detection of Events in Soccer Videos using 3D Convolutional Neural Networks}, abstract = {In this paper, we present an algorithm for automatically detecting events in soccer videos using 3D convolutional neural networks. The algorithm uses a sliding window approach to scan over a given video to detect events such as goals, yellow/red cards, and player substitutions. We test the method 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 = {2020}, journal = {2020 IEEE International Symposium on Multimedia (ISM)}, publisher = {IEEE}, doi = {10.1109/ISM.2020.00030}, }