MSVA
MSVA copied to clipboard
Deep learning model for supervised video summarization called Multi Source Visual Attention (MSVA)
Results
14
MSVA issues
Sort by
recently updated
recently updated
newest added
Hi, I noticed that the last step of the self-attention calculation doesn't seem so right: ``` att_weights_ = nn.functional.softmax(logits, dim=-1) weights = self.dropout(att_weights_) y = torch.matmul(V.transpose(1,0), weights).transpose(1,0) ``` So here...
could you help me with how to extract features of the datasets? ( I also want to train in my dataset demo)