AU-Action

Reported on 10 benchmarks across 5 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision8 results

VideoonGTEA
mAP@0.1:0.7
76.9
VideoonGTEA
mAP@0.5
66.3
Temporal Action LocalizationonGTEA
mAP@0.1:0.7
76.9
Temporal Action LocalizationonGTEA
mAP@0.5
66.3
Action LocalizationonGTEA
mAP@0.1:0.7
76.9
Action LocalizationonGTEA
mAP@0.5
66.3
Weakly Supervised Action LocalizationonGTEA
mAP@0.1:0.7
76.9
Weakly Supervised Action LocalizationonGTEA
mAP@0.5
66.3

Methodology2 results

Zero-Shot LearningonGTEA
mAP@0.1:0.7
76.9
Zero-Shot LearningonGTEA
mAP@0.5
66.3