Lisa Anne

Apr 24, 2024 | arxiv.org | Lisa Anne |A. Stevie |John Oliver |De Haas

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Apr 22, 2024 | arxiv.org | Lisa Anne

Oct 18, 2023 | arxiv.org | Lisa Anne

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

May 12, 2023 | arxiv.org | Lisa Anne

[Submitted on 12 May 2023] Title:Measuring Progress in Fine-grained Vision-and-Language Understanding Download a PDF of the paper titled Measuring Progress in Fine-grained Vision-and-Language Understanding, by Emanuele Bugliarello and 4 other authors Download PDF Abstract: While pretraining on large-scale image-text data from the Web has facilitated rapid progress on many vision-and-language (V&L) tasks, recent work has demonstrated that pretrained models lack "fine-grained" understanding,...