Sumedh Datar, R&D Senior Software Engineer at 7-Eleven, gave this presentation at the Computer Vision Festival in August 2023.

In this session, I’m going to talk about language models with computer vision. A decade back, when deep learning was proven to be the way to go towards solving problems in computer vision and natural language processing, there was no interconnect that was as good as today.

Computer vision models are very good for classification and detection techniques. Language models are very good for giving opinions, understanding the context, and understanding any language. 

So today, in this session, I'm going to talk about when you bring language models and computer vision together, and what the possibilities are that we can actually see in the AI domain.