Dong-Jin Kim
Dong-Jin Kim
That's right. The human and the object features are pre-extracted, so the model is only updated up to the region feature part.
Thank you interest in my paper. As mentioned in the paper, we count the image level statistics in order to easily obtain the co-occurrence matrix. Even though the bounding box...
Thank you interest in my paper. The pickle file for co-occurrence matrices should be loaded with Pytorch function: ``` data = torch.load('co-occurrence_pos(1).pkl') ``` If you have more questions, please feel...