List your company

Multiple-choice Audio Question Answering on TUT 2017 (test)

78.4AccuracyVideoLLaMA2-AV
64.3668.00571.6575.295Jun 11, 2024

Evaluation results

MethodLinks
VideoLLaMA2-AVSize=7B, Training Hours=5k2024.0678.4
VideoLLaMA2.1-AVSize=7B, Training Hours=5k2024.0677.28
Qwen-AudioSize=7B, Training Hours=137k2024.0664.9