xixiareone

questions about MSVD

12

The article mentions that "where they randomly chose 5 ground-truth sentences per video. We use the same setting when we compare with that approach".Does the training set, validation set and...

关于Two-Models Ensemble的问题

2

你好，我想请教论文表1中的Two-Models Ensemble这一实验，不是很能理解，想请教一下作者，是哪两种model进行ensemble呢，以及对于bert和gru又如何做不同的ensemble？ 非常感谢！

Do you experiment with the results of graph matching? In my experiment the effect is very general.

Hello, I am very interested in your work, can you share the code for visual query Many thanks!

Hello, I am very interested in your work, can you share the code for visual query Many thanks!

Hello， I am interested in your Learning Modality-Invariant Latent Representations for Generalized Zero-shot Learning, can you share the codes? Many thanks!

can you share the codes about sne? Many thanks

I am interested in your work , can you share the codes about "from .msvd_dataset import get_dataset"(msvd_dataset.py) Many thanks!

Question about how to invoke scene graph in caption_model

3

hi! In caption_model, I don't see how you invoke the code of the scene graph for each video you generated before, but instead use the data in sum data. Where...