Can Commonsense Knowledge Improve CLIP's Performance in Cross-Domain VQA?

N C, Mohamad Hassan; Jha, Ankit; Abdar, Moloud; Banerjee, Biplab

Can Commonsense Knowledge Improve CLIP's Performance in Cross-Domain VQA?

conference contribution

posted on 2025-01-22, 00:51 authored by Mohamad Hassan N C, Ankit Jha, Moloud Abdar, Biplab Banerjee

Can Commonsense Knowledge Improve CLIP's Performance in Cross-Domain VQA?

History

Related Materials

1.
DOI - Is version of https://doi.org/10.1145/3702250.3702265

Location

Bengaluru, Karnataka, India

Open access

Yes

Language

eng

Publication classification

E1 Full written paper - refereed

Pagination

1-10

Start date

2024-12-13

End date

2024-12-15

Title of proceedings

ICVGIP 2024 : Proceedings of the Fifteenth Indian Conference on Computer Vision Graphics and Image Processing

Event

Computer Vision Graphics and Image Processing. Conference (2024 : 15th : Bengaluru, Karnataka, India)

Publisher

Association for Computing Machinery

Place of publication

New York, N.Y.

Publication URL

https://doi.org/10.1145/3702250.3702265

Usage metrics

Keywords

Eye Disease and Disorders of Vision Neurosciences 1.1 Normal biological development and functioning

Licence

CC BY 4.0

Can Commonsense Knowledge Improve CLIP's Performance in Cross-Domain VQA?

History

Related Materials

Location

Open access

Language

Publication classification

Pagination

Start date

End date

Title of proceedings

Event

Publisher

Place of publication

Publication URL

Usage metrics

Categories

Keywords

Licence

Exports