AVQA Result Different from The Reported Result.

[Subrata132]

Hi,
Thank you for the great work.
I'm using audio_visual branch with VideoLLaMA2.1-7B-AV, Audio Encoder: Fine-tuned BEATs_iter3+(AS2M)(cpt2, video encoder: siglip-so400m-patch14-384.

The result found: Overall Accuracy: 65.75% Total Responses: 9185

Which is significantly lower than the reported result 80.9.

Please give me some suggestions on how to reproduce the results. Or what I'm doing incorrectly.

[Bashima]

I attempted to use the model with 9129 responses, but it only achieved an accuracy of 66%. Could the authors kindly assist in recreating the results?