hubaak

@Cecile-hi Hi, I set batch_size=16, epoch=200, lr_decay_step=150, and other hyperparameters to default. I got a score of 0.800 on the CREMA-D dataset, which is as good as expected. Here is...

> @hubaak Hi! I’d like to know how you implemented the uni-modal late fusion algorithm. Did you simply add a single-layer MLP after the ResNet? And did this achieve a...

> i just find that the eq.8 can be simplifed as follow:  it just may be a softmax as follow:  Yeah, they simply weight the outputs of models...