EM-MIL

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 Vision4 results

VideoonTHUMOS’14
mAP@0.5· 2020-03-31
30.5
best: 45.3 (LACP)
SOTA
Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning arXiv:2004.00163
Temporal Action LocalizationonTHUMOS’14
mAP@0.5· 2020-03-31
30.5
best: 45.3 (LACP)
SOTA
Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning arXiv:2004.00163
Action LocalizationonTHUMOS’14
mAP@0.5· 2020-03-31
30.5
best: 45.3 (LACP)
SOTA
Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning arXiv:2004.00163
Weakly Supervised Action LocalizationonTHUMOS’14
mAP@0.5· 2020-03-31
30.5
best: 45.3 (LACP)
SOTA
Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning arXiv:2004.00163

Methodology1 result

Zero-Shot LearningonTHUMOS’14
mAP@0.5· 2020-03-31
30.5
best: 45.3 (LACP)
SOTA
Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning arXiv:2004.00163