Action Segmentation On Breakfast 1
평가 지표
Acc
Average F1
Edit
F1@10%
F1@25%
F1@50%
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Acc | Average F1 | Edit | F1@10% | F1@25% | F1@50% |
|---|---|---|---|---|---|---|
| efficient-u-transformer-with-boundary-aware | 75 | 69.3 | 74.6 | 76.2 | 71.8 | 59.8 |
| asquery-a-query-based-model-for-action | 77.9 | 74.6 | 78.4 | 80.7 | 76.5 | 66.5 |
| leveraging-triplet-loss-for-unsupervised | 63.2 | - | - | - | - | - |
| action-segmentation-with-joint-self | 70.2 | 66.4 | 73.7 | 75.0 | 69.1 | 55.2 |
| global2local-efficient-structure-search-for | 70.8 | 66.9 | 74.5 | 76.3 | 69.9 | 54.6 |
| sf-tmn-slowfast-temporal-modeling-network-for | 77.0 | 71.6 | 77.0 | 78.7 | 74.0 | 62.2 |
| temporally-weighted-hierarchical-clustering | 62.7 | - | - | - | - | - |
| alleviating-over-segmentation-errors-by | 67.6 | 66.4 | 72.4 | 74.3 | 68.9 | 56.1 |
| leveraging-triplet-loss-for-unsupervised | 65.1 | - | - | - | - | - |
| leveraging-triplet-loss-for-unsupervised | 63.7 | - | - | - | - | - |
| efficient-two-step-networks-for-temporal | 67.8 | 66.4 | 70.3 | 74.0 | 69.0 | 56.2 |
| maximization-and-restoration-action | 71.7 | 67.9 | 75.1 | 75.6 | 70.5 | 57.6 |
| fact-frame-action-cross-attention-temporal | 76.2 | 74.7 | 79.7 | 81.4 | 76.5 | 66.2 |
| cross-enhancement-transformer-for-action | 74.9 | 71.8 | 77.8 | 79.3 | 74.3 | 61.9 |
| diffusion-action-segmentation | 76.4 | 73.6 | 78.4 | 80.3 | 75.9 | 64.6 |
| depthwise-separable-temporal-convolutional | 70.75 | 59.6 | 69.02 | 67.70 | 62.05 | 49.18 |
| refining-action-segmentation-with | 69.4 | 67.1 | 71.9 | 74.7 | 69.5 | 57.0 |
| aspnet-action-segmentation-with-shared | 75.9 | 70.6 | 76.3 | 78.1 | 72.9 | 60.8 |
| ms-tcn-multi-stage-temporal-convolutional | 65.1 | 50.6 | 61.4 | 58.2 | 52.9 | 40.8 |
| unified-fully-and-timestamp-supervised | 69.7 | 68.8 | 77.1 | 76.9 | 71.5 | 58 |
| coarse-to-fine-multi-resolution-temporal | 76.0 | 66.2 | 69.6 | 72.2 | 68.7 | 57.6 |
| adafocus-towards-end-to-end-weakly-supervised | 78.0 | 76.2 | 78.3 | 82.1 | 79.0 | 67.5 |
| fifa-fast-inference-approximation-for-action | 68.6 | 66.8 | 78.5 | 75.5 | 70.2 | 54.8 |
| how-much-temporal-long-term-context-is-needed | 74.2 | 70.1 | 77.0 | 77.6 | 72.6 | 60.1 |
| ms-tcn-multi-stage-temporal-convolutional | 66.3 | 46.2 | 61.7 | 52.6 | 48.1 | 37.9 |
| rf-next-efficient-receptive-field-search-for | 70.8 | - | - | - | - | - |
| weakly-supervised-action-segmentation-using | 62.8 | 62.6 | 76.3 | 73.2 | 66.1 | 48.4 |
| ms-tcn-multi-stage-temporal-convolutional-2 | 67.6 | 56.2 | 65.6 | 64.1 | 58.6 | 45.9 |
| efficient-temporal-action-segmentation-via | 76.6 | 72.4 | 77.3 | 79.2 | 74.9 | 63.2 |
| temporal-relational-modeling-with-self | 68.3 | 59.1 | 68.9 | 68.7 | 61.9 | 46.6 |
| unsupervised-discriminative-embedding-for-sub | 47.4 | - | - | - | - | 31.9 |
| asformer-transformer-for-action-segmentation | 73.5 | 68.0 | 75.0 | 76.0 | 70.6 | 57.4 |
| action-segmentation-with-mixed-temporal | 71.0 | 66.4 | 73.6 | 74.2 | 68.6 | 56.5 |
| boundary-aware-cascade-networks-for-temporal | 70.4 | 63.1 | 66.2 | 68.7 | 65.5 | 55.0 |
| bit-bi-level-temporal-modeling-for-efficient | 75.5 | 73.7 | 79.0 | 80.6 | 75.8 | 64.7 |
| ms-tcn-multi-stage-temporal-convolutional-2 | 67.3 | 55.2 | 64.9 | 63.3 | 57.7 | 44.5 |
| improving-action-segmentation-via-graph-based | 65.0 | 51.6 | 58.7 | 57.5 | 54.0 | 43.3 |