Questions about text feature dimenstion #6

Open

opened

on Oct 13, 2022

When I was loading the iemocap_features_4 pickle file. The video_text data is shown to be size 100. But you mentioned in your paper, the textual features' size is 768 extracted using sBERT. Could you please explain this?

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

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