An LSTM trained on MediaPipe blendshapes reports 71% accuracy on a three-class version of FER2013, but the claimed match to the seven-class benchmark is unsupported.
Comparison of facial landmark detection methods for micro-expressions analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Emotion estimation from video footage with LSTM
An LSTM trained on MediaPipe blendshapes reports 71% accuracy on a three-class version of FER2013, but the claimed match to the seven-class benchmark is unsupported.