cfeng16/audio-visual-forensics

code release

Closed this issue · 10 comments

Mrfortuante commented

Thanks for releasing part of codes.
By the way, may I ask could you release the code of loading data first?
Thanks a lot.

Mrfortuante commented

Thanks, can you share the demo script?

mowen9 commented

Did you obtain the code of loading data?

Mrfortuante commented

Did you obtain the code of loading data?

@mowen9 No, the author provides very limited information.

Mrfortuante commented

@cfeng16 Hello, can you release the demo script? Current code is too limit to re-implement. Plz.

Mrfortuante commented

I just wonder that does it really so hard to release the completed code?

mowen9 commented

I just wonder that does it really so hard to release the completed code?

I also wonder whether he will release the completed code.

Mrfortuante commented

I just wonder that does it really so hard to release the completed code?

I also wonder whether he will release the completed code.

@mowen9 Hi, have you try to reimplement his code?

mowen9 commented

I just wonder that does it really so hard to release the completed code?

I also wonder whether he will release the completed code.

@mowen9 Hi, have you try to reimplement his code?

Yes! However, his code contains too little information, which is not enough to reproduce the results.
There is too little publicly available code in the audio-visual deepfake detection task. This task is too difficult to perform.

cfeng16 commented

I'll release them, sorry for the delay

cfeng16 commented

I have updated the codebase. Please let me know if you have any questions