Event Detection on NHL dataset
0.7778Faceoff Precisionmulti-tower temporal convolutional network
Evaluation results
| Method | Links | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| multi-tower temporal convolutional networkSliding window stride=1 second, Post processing=true, Tolerance (delta)=1 second, Weighted cross entropy loss=true, Adam optimizer=true, Initial learning rate=0.0012020.04 | 0.7778 | 0.5676 | 0.6562 | 0.5274 | 0.4486 | 0.4849 | 0.3223 | 0.4488 | 0.407 | 0.5142 | 0.8848 | 0.6504 | 0.5354 | 0.5874 | 0.5497 |