Individual Activity Recognition on Volleyball (test)
85.9AccuracyActor-Transformers
Evaluation Results
| Method | Links | |
|---|---|---|
| Actor-Transformersbounding boxes=ground-truth2022.07 | 85.9 | |
| GroupFormerbounding boxes=ground-truth2022.07 | 85.6 | |
| Ehsanpour et al.bounding boxes=ground-truth2022.07 | 83.3 | |
| multi-stream convolutional neural network frameworkInput Frames=Multiple Frames2018.12 | 83.15 | |
| ARGBackbone=VGG16, Bounding box source=GT2019.04 | 83.1 | |
| Pramono et al.bounding boxes=ground-truth2022.07 | 83.1 | |
| ARGBackbone=Inception-v3, Bounding box source=GT2019.04 | 83 | |
| ARGbounding boxes=ground-truth2022.07 | 83 | |
| ARGBackbone=VGG19, Bounding box source=GT2019.04 | 82.6 | |
| Social SceneInput Frames=Multiple Frames2018.12 | 82.4 | |
| SSUBackbone=Inception-v3, Bounding box source=GT2019.04 | 81.8 | |
| SSUbounding boxes=ground-truth2022.07 | 81.8 | |
| multi-stream convolutional neural network frameworkInput Frames=Single Frame2018.12 | 81.56 | |
| Social SceneInput Frames=Single Frame2018.12 | 81.1 | |
| SSUBackbone=Inception-v3, Bounding box source=PRO2019.04 | 77.4 | |
| CERNInput Frames=Multiple Frames2018.12 | 69.1 | |
| HGC-Transformerbounding boxes=predicted2022.07 | 65 | |
| Ehsanpour et al.bounding boxes=predicted2022.07 | 41.8 | |
| ARGbounding boxes=predicted2022.07 | 39.8 |