2025

Maniparambil, Mayug ORCID: 0000-0002-9976-1920 (2025) Aligning Vision and Language: Harnessing Language Semantics for Efficient Vision Models. PhD thesis, Dublin City University.

2024

Aleem, Sidra, Wang, Fangyijie, Maniparambil, Mayug ORCID: 0000-0002-9976-1920, Arazo, Eric, Dietlmeier, Julia ORCID: 0000-0001-9980-0910, Curran, Kathleen M. ORCID: 0000-0003-0095-9337, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 and Little, Suzanne ORCID: 0000-0003-3281-3471 (2024) Test-time adaptation with salip: A cascade of sam and clip for zero-shot medical image segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

2023

Maniparambil, Mayug, Vorster, Chris, Molloy, Derek, Murphy, Noel, McGuinness, Kevin ORCID: 0000-0003-1336-6477 and O'Connor, Noel E. ORCID: 0000-0002-4033-9135 (2023) Enhancing clip with gpt-4: harnessing visual descriptions as prompts. In: International Conference on Computer Vision Workshops 2023, 2-6 Oct 2023, Paris.

2022

Maniparambil, Mayug ORCID: 0000-0002-9976-1920, McGuinness, Kevin ORCID: 0000-0003-1336-6477 and O'Connor, Noel E. ORCID: 0000-0002-4033-9135 (2022) Base transformers: attention over base data-points for one shot learning. In: 33rd British Machine Vision Conference, 21-24 Nov 2022, London.