Action Detection On Ucf101 24
评估指标
Video-mAP 0.2
Video-mAP 0.5
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Video-mAP 0.2 | Video-mAP 0.5 |
|---|---|---|
| hierarchical-self-attention-network-for | 82.30 | 51.47 |
| multi-region-two-stream-r-cnn-for-action | - | - |
| multi-region-two-stream-r-cnn-for-action | - | - |
| step-spatio-temporal-progressive-learning-for | 76.6 | - |
| tacnet-transition-aware-context-network-for-1 | 77.5 | 52.9 |
| ava-a-video-dataset-of-spatio-temporally | - | 59.9 |
| holistic-interaction-transformer-network-for | 88.8 | 74.3 |
| hierarchical-self-attention-network-for | 80.42 | 49.50 |
| you-only-watch-once-a-unified-cnn | 75.8 | 48.8 |
| actions-as-moving-points | 81.8 | 53.9 |
| tube-convolutional-neural-network-t-cnn-for | 47.1 | - |
| you-only-watch-once-a-unified-cnn | 78.6 | 53.1 |
| dance-with-flow-two-in-one-stream-action | 75.48 | 48.31 |
| dance-with-flow-two-in-one-stream-action | 78.48 | 50.30 |
| finding-action-tubes-with-a-sparse-to-dense | - | 54 |
| end-to-end-semi-supervised-learning-for-video | - | 72.1 |
| stable-mean-teacher-for-semi-supervised-video | - | 76.3 |
| end-to-end-spatio-temporal-action | 88.0 | 71.8 |