Skip to content

Scoring a video #70

Description

@jenjamc

Hi TRIBEv2 team,

We integrated TRIBEv2 following your guide and successfully got predictions from videos:

preds, segments = model.predict(events=df)

We are not neuroscientists — we are software engineers building a product for non-technical users. We can get the brain activation image, but we do not know what to do with it next.

We have two simple questions:

  1. How do we turn preds into a single meaningful score that tells us whether a video is engaging or not? What is the simplest correct way to do this?

  2. How do we translate that score into something a non-technical user can understand — for example, "your video strongly activates visual and emotional areas" or a score from 0 to 100?

We are not looking for academic precision — just your recommendation on the simplest valid approach to make the output useful for everyday users.

Thank you!

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions