3min chapter

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

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode