How can i use this code to train regions & snippets RNN model?

[lebronze]

In this code, i only find how to use images and the images description sentences to train a multimodal RNN. But i don't see any founctions about how to use the regions & snippets to train the model.Just like the figure 5 or part 4.3 in the paper.
How can i train my own model? How can i get the result just like the figure 5?

[Utsavz]

@lebronze Did you find out the solution method to the problem? If yes, please answer

[lebronze]

Sorry @Utsavz ,the author of this code said he only provided the generating stage in the paper , but didn't provide the alignment stage.
Maybe you can send an email to him for some help.

[Utsavz]

Thank you @lebronze for the help.