A multi-modal two-time-scale framework with progressive training is claimed to beat prior work on LIRIS-ACCEDE, but the results rely on test-set parameter selection and do not improve arousal MSE.
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
REJECT 1representative citing papers
citing papers explorer
-
Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context
A multi-modal two-time-scale framework with progressive training is claimed to beat prior work on LIRIS-ACCEDE, but the results rely on test-set parameter selection and do not improve arousal MSE.