Noel E. O'Connor

Do Vision and Language Encoders Represent the World Similarly?

CVPR 2024 1

From Unimodal to Multimodal: Scaling up Projectors to Align Modalities

arXiv 2024

An accurate detection is not all you need to combat label noise in web-noisy datasets

arXiv 2024

Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts

arXiv 2023

Mayug Maniparambil

Kevin McGuinness

Raiymbek Akshulakov

Sanath Narayan

Yasser Abdelaziz Dahou Djilali

Ankit Singh

Chris Vorster

Derek Molloy

Eric Arazo

Jack Valmadre