Hi! I'm Rahul
I'm building multimodal AI systems that help us unpack and understand visual storytelling.
OZU is a new kind of straming platform for people to discover and explore stories. I'm the co-founder and head of ML. We're building narrative intelligence to understand stories at scale.
I was invited to give an talk at the inaugral CVEU 2021 workshop. We presented CinemaNet, a jointly trained multi-task classification model that codifies a comprehensive taxonomy of cinematography.
A flagship interactive retail experience for HBO Max & AT&T, in collaboration with HUSH, where users could interact with parts of the HBO archive in real-time with gestures and words.
A collaborative project with IYOIYO studio / Google & YouTube. I built custom vision models that helped power the visual intelligence behind the experience.
Blog post introducing the basics of visual language in cinema, and a custom model and dataset built to recognise different types of framing.