Improving Action Segmentation via Graph-Based Temporal Reasoning
Open paper
Benchmark
Model
Rank
Results
action-segmentation-on-breakfast
GTRM
–
Average F1: 51.6
F1@50%: 43.3
F1@25%: 54.0
F1@10%: 57.5
Edit: 58.7
…
Rank counts only results with a code link.