MLAD

Reported on 5 benchmarks across 5 tasks · 1 paper · 5 SOTA

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· 2021-03-04
14.2
best: 37.5 (TriDet (VideoMAEv2))
SOTA
Modeling Multi-Label Action Dependencies for Temporal Action Localization arXiv:2103.03027
Temporal Action LocalizationonMultiTHUMOS
Average mAP· 2021-03-04
14.2
best: 37.5 (TriDet (VideoMAEv2))
SOTA
Modeling Multi-Label Action Dependencies for Temporal Action Localization arXiv:2103.03027
Action LocalizationonMultiTHUMOS
Average mAP· 2021-03-04
14.2
best: 37.5 (TriDet (VideoMAEv2))
SOTA
Modeling Multi-Label Action Dependencies for Temporal Action Localization arXiv:2103.03027

Methodology1 result

Zero-Shot LearningonMultiTHUMOS
Average mAP· 2021-03-04
14.2
best: 37.5 (TriDet (VideoMAEv2))
SOTA
Modeling Multi-Label Action Dependencies for Temporal Action Localization arXiv:2103.03027

Time Series1 result

Action DetectiononMulti-THUMOS
mAP· 2021-03-04
51.5
SOTA
Modeling Multi-Label Action Dependencies for Temporal Action Localization arXiv:2103.03027