Skip to content

Question about video qa #8

@Yangget

Description

@Yangget

Hello author, thanks for your recipe on video text learning.

I have a question: how to use VindLU_QA for video description generation. I see that you are in the paper, which only involves video Q&A (yes or no type and multiple choice).

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions