MS-TCT

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· 2021-12-07
16.2
best: 37.5 (TriDet (VideoMAEv2))
SOTA
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection arXiv:2112.03902
Temporal Action LocalizationonMultiTHUMOS
Average mAP· 2021-12-07
16.2
best: 37.5 (TriDet (VideoMAEv2))
SOTA
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection arXiv:2112.03902
Action LocalizationonMultiTHUMOS
Average mAP· 2021-12-07
16.2
best: 37.5 (TriDet (VideoMAEv2))
SOTA
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection arXiv:2112.03902

Methodology1 result

Zero-Shot LearningonMultiTHUMOS
Average mAP· 2021-12-07
16.2
best: 37.5 (TriDet (VideoMAEv2))
SOTA
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection arXiv:2112.03902

Time Series1 result

Action DetectiononTSU
Frame-mAP· 2021-12-07
33.7
SOTA
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection arXiv:2112.03902