Visual Question Answering

topic on 1 show · 2 statements across 1 episodes

the MAD Podcast

2 statements about Visual Question Answering, every show

MAD Assertion Partly supported
Bordes: Visual QA models saturate around 60% accuracy versus 95% for humans
“Basically many methods actually saturated at like, I don't know, 55 or 60% accuracy. Ah, the simpler or the most complicated were actually in the same ballpark. Whereas human can actually go up to 95”
Antoine Bordes Nov 9, 2016 ▶ 27:25 Artificial Intelligence at Facebook // Antoine Bordes, Facebook [FirstMark's Data Driven]
MAD Insight
Visual question answering is harder than captioning because it requires reasoning
“So, what people try to do now is that to move to caption what's called caption generation, which was actually super promising, but actually people realized that actually the machine wasn't that good, to what's called now visual question answering, which is mor…”
Antoine Bordes Nov 9, 2016 ▶ 9:15 Artificial Intelligence at Facebook // Antoine Bordes, Facebook [FirstMark's Data Driven]

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.