The Multimodal Adaptation Gate lets BERT and XLNet be fine-tuned with visual and acoustic inputs, improving multimodal sentiment analysis and reaching human-level scores on CMU-MOSI.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Integrating Multimodal Information in Large Pretrained Transformers
The Multimodal Adaptation Gate lets BERT and XLNet be fine-tuned with visual and acoustic inputs, improving multimodal sentiment analysis and reaching human-level scores on CMU-MOSI.