DCCN icon indicating copy to clipboard operation
DCCN copied to clipboard

Code for "Dynamic Context-guided Capsule Network for Multimodal Machine Translation" (ACM MM2020)

Results 3 DCCN issues
Sort by recently updated
recently updated
newest added

It is mentioned To preprocess image data, please refer to https://github.com/peteanderson80/bottom-up-attention. But there is no such clear instruction on the github page. Can someone post detailed instructions?

Hi, Can you tell me what the image mask (from `path_to_train_img_mask` and `path_to_valid_img_mask` below) is and what it is used for? Thanks. ``` python train_mmod.py \ -data demo \ -save_model...

Hi,thanks for your work and code. How long does model training take? Can you provide the checkpoints file? I want to test it.