Here we describe a new approach to train a video captioning neural network , that is not only based on the normal cross entropy loss for the caption but also uses the meaning of the caption.
Hi! Thanks for the great work!
I'm trying to follow your instructions and encounter some files that I did not quite know how to prepare.
Can you give more details on these files? wordtoindex.pickle, indextoword.pickle, embedding.npy
Thank you and looking forward to your response!
Hey @captanlevi
Thanks for open sourcing such an awesome work!!!
I wanted to run inference using your pre-trained models, however I cannot find the link to download the same. Also could please provide some help with instructions on the prerequisites for the same?