mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video (ICML 2023)
213
stars
17
forks
source link
Is the zero-shot performance of VideoQA in Table 20 from the model finetuned on ImageQA dataset? #6
Open
tgyy1995 opened 1 year ago
@tgyy1995 Have you found the answer yet? I have the same question.