A multi-level attention network fusing text, audio, and video features achieves lower RMSE than the AVEC 2019 baseline for PHQ-8 depression prediction on the development split, while the hidden test split was used only for the text-only model.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-level Attention network using text, audio and video for Depression Prediction
A multi-level attention network fusing text, audio, and video features achieves lower RMSE than the AVEC 2019 baseline for PHQ-8 depression prediction on the development split, while the hidden test split was used only for the text-only model.