F1@10%: 85.1Edit: 81.9Acc: 85.9F1@25%: 85.4
Papers with Code · CC BY-SA 4.0
Action Segmentation
Action Segmentation is a challenging problem in high-level video understanding. In its simplest form, Action Segmentation aims to segment a temporally untrimmed video by time and label each segmented part with one of pre-defined action labels. The results of Action Segmentation can be further used as input to various applications, such as video-to-text and action localization.
<span class="description-source">Source: TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation </span>
논문
F1@10%: 80.7Edit: 74.3Acc: 83.7F1@25%: 78.5
Acc: 66.5
F1@10%: 83.0Edit: 75.8Acc: 83.2F1@25%: 81.5
F1@10%: 82.0Edit: 75.2Acc: 83.2F1@25%: 80.1
F1@10%: 84.9Edit: 79.3Acc: 84.5F1@25%: 83.5
F1@10%: 92.7Edit: 87.5Acc: 91.4F1@25%: 91.6
F1@10%: 82.3Edit: 74.3Acc: 84.4F1@25%: 81.3
F1@10%: 89.2Edit: 83.8Acc: 88.1F1@25%: 87.8
F1@10%: 84.3Edit: 76.4Acc: 84.9F1@25%: 81.8
F1@10%: 87.6Edit: 81.7Acc: 86.9F1@25%: 86.5
F1@10%: 77.0Edit: 70.0Acc: 80.0F1@25%: 74.43
F1@10%: 90.1Edit: 85.0Acc: 88.9F1@25%: 89.2
F1@10%: 89.2Edit: 82.9Acc: 87.4F1@25%: 87.5
F1@10%: 89.3Edit: 84.2Acc: 89.5F1@25%: 88.4
F1@10%: 85.2Edit: 78.8Acc: 82.0F1@25%: 83.9
F1@10%: 80.3Edit: 73.4Acc: 82.2F1@25%: 78
F1@10%: 89.4Edit: 83.2Acc: 87.7F1@25%: 87.7
F1@10%: 84.4Edit: 77.0Acc: 77.9F1@25%: 81.3
F1@10%: 87.8Edit: 82.0Acc: 87.2F1@25%: 86.3
F1@10%: 76.3Edit: 67.9Acc: 80.7F1@25%: 74.0
F1@10%: 86.6Edit: 81.0Acc: 83.9F1@25%: 85.7
Edit Distance: 89.3±5.2Accuracy: 87.9±4.2
F1@10%: 91.5Edit: 89.1Acc: 88.6F1@25%: 90.2
F1@10%: 89.1Edit: 84.4Acc: 89.8F1@25%: 88.0
F1@10%: 79.1Edit: 72Acc: 80F1@25%: 75.9
F1@10%: 89.1Edit: 83.9Acc: 87.4F1@25%: 87.6