Computer Vision

This lecture was delivered by Arsha Nagrani, a recent Ph.D. graduate from Oxford University's VGG group, and an incoming research scientist at Google Research, titled Multimodality for Video Understanding

This Lecture was presented by Rahul Sukthankar, a research scientist at Google Research and Adjunct Prof. at CMU. It was titled Deep Learning in Computer Vision

This lecture was presented by Cristian Sminchisescu, a professor at Lund University and working at Google Research. The lecture was titled End-to-end Generative 3D Human Shape and Pose models, and active human sensing

This lecture was delivered by Neil Houlsby, currently working in Google Brain, Zurich, on Large Scale Visual Representation Learning

An article about our experience of taking part in our first hackathon

Used ConvNets to detect tornado damage done to buildings, using semantic segmentation.