| Paper | Code | Accuracy (%) | ModelName | ReleaseDate |
|---|---|---|---|---|
| Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors | 94.4 | DEEP-HAL with ODF+SDF (I3D) | 2020-01-14 | |
| High-order Tensor Pooling with Attention for Action Recognition | 93.1 | TO+MaxExp+IDT | 2021-10-11 | |
| Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs | 92.6 | HAF+BoW/FV halluc. | 2019-06-13 | |
| High-order Tensor Pooling with Attention for Action Recognition | 92.5 | SO+MaxExp+IDT | 2021-10-11 | |
| HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN | ✓ Link | 84.44 | HalluciNet (ResNet-50) | 2019-12-10 |