Two Stream Network for Stroke Detection in Table Tennis

16 Dec 2021  ·  Anam Zahra, Pierre-Etienne Martin ·

This paper presents a table tennis stroke detection method from videos. The method relies on a two-stream Convolutional Neural Network processing in parallel the RGB Stream and its computed optical flow. The method has been developed as part of the MediaEval 2021 benchmark for the Sport task. Our contribution did not outperform the provided baseline on the test set but has performed the best among the other participants with regard to the mAP metric.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Detection TTStroke-21 ME21 Two Stream Network IoU 0.070 # 2
mAP 0.00124 # 2

Methods


No methods listed for this paper. Add relevant methods here