Vision to Language
About this video
Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceCovers vision-to-language systems that generate text descriptions from images. Teaches multimodal machine learning and neural architecture design.
A 80-minute video from Microsoft Research: “Vision to Language”.
Video by Microsoft Research, played through YouTube's embedded player.
Part of Faculty Summit 2015