Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos

Open paper
Benchmark Model Rank Results
action-segmentation-on-50-salads-1Semantic2Graph–F1@50%: 87.3F1@25%: 90.2F1@10%: 91.5Acc: 88.6Edit: 89.1
action-segmentation-on-gtea-1Semantic2Graph–F1@50%: 91.3F1@25%: 94.2F1@10%: 95.7Acc: 89.8Edit: 92.0

Rank counts only results with a code link.