Monikshah

Do you consider the predicates in the captions of each test image as the ground truth predicates?

Awesome! Thank you very much. :)

I have one more question. We develop positive and negative bag for each predicate and train them separately. If we train them separately we will have separate models. For example,...

Sure. Thank you very much!

> Can I ask you some details about the training? For different predicates, the division of positive bags and negative bags is different. How do you realize batch training? In...

Hello author, Thank you so much for being very helpful. I have some more questions, It would very kind of you if you can share how you resolved these; 1....

For the test data we don't know the predicate so how did you form the bag?