-
Hi,
Congrats on your amazing work! Can you please upload the MSVD checkpoint and steps for inference?
-
I can find json file name for MSVD zero shot evaluation f"{anno_root_downstream}/msvd_ret_train.json",
in VideoMamba/videomamba/video_mm/exp_zs/msvd/config.py file.
But, I didn't find correspondin…
-
why i can't download the msvd_dataset feature ,it's empty, don't contain any .npy files.
thanks for your answer.
-
Thank you for your excellent work. Can you provide the code to train and test on MSVD?
-
Hello, thanks for providing the code!
In regards to the models used for generating the results in the paper, is this uploaded anywhere that can be shared? I would be interested in the inference wit…
-
I get .csv file of MSVD dataset. How can I get video from the file and use it in extract_RGB_feats.py?
-
Hi! Thanks for the great work and open source code.
I noticed that Activitynet's video frame data is used for inference, as shown in the code below.
[frame='/Path/to/video_chatgpt/activitynet_fr…
-
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 test set …
-
Hey - I am unable to reproduce the reported zero-shot results. So far I tried it on MSRVTT and MSVD, I would appreciate it if you kindly have a look.
Here is what I got after running these 2 script…
-
Do you use some tricks in the training of the MSVD dataset? We found that the experimental results on this dataset could not achieve the visual quality and FID score in the paper.