PDAN

Reported on 6 benchmarks across 5 tasks

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

Computer Vision3 results

VideoonMultiTHUMOS
Average mAP
17.3
best: 37.5 (TriDet (VideoMAEv2))
Temporal Action LocalizationonMultiTHUMOS
Average mAP
17.3
best: 37.5 (TriDet (VideoMAEv2))
Action LocalizationonMultiTHUMOS
Average mAP
17.3
best: 37.5 (TriDet (VideoMAEv2))

Time Series2 results

Action DetectiononMulti-THUMOS
mAP
47.6
best: 51.5 (MLAD)
Action DetectiononTSU
Frame-mAP
32.7
best: 33.7 (MS-TCT)

Methodology1 result

Zero-Shot LearningonMultiTHUMOS
Average mAP
17.3
best: 37.5 (TriDet (VideoMAEv2))