Yangyang Guo
Yangyang Guo
Could you please share the pre-trained image features from Visual Genome? This would greatly ease the affliction of ones without too much knowledge of caffe. Thanks.
There are three questions confusing me, some of them may largely affect the final performance. 1. When filtering answers, only the 'multiple_choice_answer' answer sets are pre-processed, [as shown in this...
Hi, Thank you for your code. As I go deeply into this code, I found the training step is particular slow. The problem here (I guess) is the dataset construction...
Hi Authors, Thank you for your great piece of work! Can I check with you how you computed the KL divergence between aligned and unaligned models? For example, the aligned...