This repository contains various models targetting multimodal representation learning, multimodal fusion for downstream tasks such as multimodal sentiment analysis.
Hi
how can we fit our own dataset .
Are models classifying the sentiment of speaker -
based on tone of speech, what they speech, with what facial expression do they speak ?
Hi how can we fit our own dataset . Are models classifying the sentiment of speaker - based on tone of speech, what they speech, with what facial expression do they speak ?
Regards Jaideep