Action Recognition On Diving 48
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| object-region-video-transformers-1 | 88.0 |
| vimpac-video-pre-training-via-masked-token | 85.5 |
| slowfast-networks-for-video-recognition | 77.6 |
| extending-video-masked-autoencoders-to-128-1 | 94.9 |
| learning-correlation-structures-for-vision | 88.3 |
| is-space-time-attention-all-you-need-for | 75 |
| dual-path-adaptation-from-image-to-video | 88.7 |
| is-space-time-attention-all-you-need-for | 78 |
| tfcnet-temporal-fully-connected-networks-for | 88.3 |
| video-focalnets-spatio-temporal-focal | 90.8 |
| aim-adapting-image-models-for-efficient-video | 90.6 |
| relational-self-attention-what-s-missing-in | 84.2 |
| group-contextualization-for-video-recognition | 87.6 |
| bevt-bert-pretraining-of-video-transformers | 86.7 |
| pmi-sampler-patch-similarity-guided-frame | 81.3 |
| temporal-query-networks-for-fine-grained | 81.8 |
| is-space-time-attention-all-you-need-for | 81 |
| spatiotemporal-self-attention-modeling-with | 86 |