Weaviate Podcast cover image

Unstructured with Brian Raymond - Weaviate Podcast #48!

Weaviate Podcast

CHAPTER

How to Draw a Binding Box Around an Image Caption

A lot of the approaches to date have been okay, and for bounding boxes around around document elements. Some models that work pretty well on that we've been doing a lot of really focused work on with swing transformers. We're using an OCR list approach with so it's a vision encoder and then a text decoder in order to do the jump from image in to JSON out. So our goal is by mid summer to have a wide range of different kind of like arrows in our quiver that our users can can use to get over that hump and to get to that cleanJSON.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner