AI image captioning insights with Annika Lindh

Hello folk’s episode 11 arrived, 2 months or so passed by since last podcast. This 1 is a good one, we are always trying to produce content that is high quality and relevant for blind and visually impaired folks.

Lately, many posts contain a lot of AI content, just because I really believe in the power of AI and its capabilities for the future. So, this content is prepping you what’s next and hopefully provide some useful ideas and information for entertainment and education purposes. So, let’s continue with the episode description shall we…

Annika offers insights on the AI image captioning technology, and explains what it is, how it works, and what are the current struggles. Currently, she is doing research on image captioning for blind and vision impaired individuals at TU (Technological University Dublin)

We haven’t stop recording when we covered the basics of AI image captioning, not at all, we took deep dive in to more advanced topics like using synthetic data for neural network training, as well as result benchmarking, and way more.

This podcast is full of insights and should satisfy beginners as well as geekiest users. As far as I remember we covered way more topics than image captioning…So, tune in for the latest episode…