Search Results - "Turban Ndjeuha, Mark A" :: K.UTB vyhledávací portál

Caption-Driven Explorations: Aligning Image and Text Embeddings through Human-Inspired Foveated Vision

by Zanca, Dario, Zugarini, Andrea, Dietz, Simon, Altstidl, Thomas R, Ndjeuha, Mark A. Turban, Schwinn, Leo, Eskofier, Bjoern
Year of Publication 19.08.2024

Get full text

Journal Article

Loading…

Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors

by Zanca, Dario, Zugarini, Andrea, Dietz, Simon, Altstidl, Thomas R, Ndjeuha, Mark A. Turban, Schwinn, Leo, Eskofier, Bjoern
Year of Publication 21.05.2023

Get full text

Journal Article

Loading…

Caption-Driven Explorations: Aligning Image and Text Embeddings through Human-Inspired Foveated Vision

by Zanca, Dario, Zugarini, Andrea, Dietz, Simon, Altstidl, Thomas R, Turban Ndjeuha, Mark A, Schwinn, Leo, Eskofier, Bjoern
Published in arXiv.org (19.08.2024)

Get full text

Paper

Loading…

Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors

by Zanca, Dario, Zugarini, Andrea, Dietz, Simon, Altstidl, Thomas R, Turban Ndjeuha, Mark A, Schwinn, Leo, Eskofier, Bjoern
Published in arXiv.org (23.05.2023)

Get full text

Paper

Caption-Driven Explorations: Aligning Image and Text Embeddings through Human-Inspired Foveated Vision

Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors

Caption-Driven Explorations: Aligning Image and Text Embeddings through Human-Inspired Foveated Vision

Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors

Refine Results

Format

Subject Area

Topic

Language

Year of Publication

Database