| Pre-trained | CNN backbone | UCF-101% |
---|
Two stream CNN [9] | ImageNet | VGG16 | 88.7 |
Conv + LSTM [8] | ImageNet | AlexNet | 69.1 |
C3D [18] | ImageNet | VGG11 | 82.3 |
RGB-I3D [19] | ImageNet | Inception v1 | 84.5 |
TSN [20] | ImageNet | Inception v2 | 86.4 |
3D Hybrid Model [21] | 2D CNN | C3D | 89.4 |
Two-stream model | ImageNet | DenseNet | 92.5 |
(proposed model) | | | |
- The accuracy is the average accuracy for all three splits of the dataset