Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Selective Feature reduction via cross modal query #25

Open
insafim opened this issue Nov 30, 2024 · 1 comment
Open

Selective Feature reduction via cross modal query #25

insafim opened this issue Nov 30, 2024 · 1 comment

Comments

@insafim
Copy link

insafim commented Nov 30, 2024

How does the model understand which tokens to get rid of for a question like “Describe this video in detail”.

Also what sort of an inpact does an instruction like “Select the best option among (A,B,C,D)” or any other intruction sent along with the question have on this part.

@xiaoqian-shen
Copy link
Collaborator

Hi, @insafim

Thanks for raising this concern.

(i) The query dependent token compression is designed for VQA task, which is not effective to question such as "Describe this video in detail". However, the irrelevant frames will not be removed, but reduce to low resolution tokens.

(ii) The impact of candidates options is minimum, but you can also use add special token as a placeholder to identify the question-only tokens and remove the other instruction.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants