Action Recognition On Real Life Violence
Metrics
accuracy
Results
Performance results of various models on this benchmark
Model Name | accuracy | Paper Title | Repository |
|---|---|---|---|
| DeVTr | 96.25% | Data Efficient Video Transformer for Violence Detection | |
| CNN+LSTM | 88.8% | Violence Recognition from Videos using Deep Learning Techniques | - |
| Temporal Fusion cnn+lstm | 91% | A Temporal Fusion Approach for Video Classification with Convolutional and LSTM Neural Networks Applied to Violence Detection | - |
0 of 3 row(s) selected.