Stable Mean Teacher with an Error Recovery module and a Difference of Pixels constraint improves semi-supervised video action detection, reaching near fully-supervised accuracy with 10-20% labels.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Stable Mean Teacher for Semi-supervised Video Action Detection
Stable Mean Teacher with an Error Recovery module and a Difference of Pixels constraint improves semi-supervised video action detection, reaching near fully-supervised accuracy with 10-20% labels.