I’m working on building a video classification service in the Computer Vision team. I’ve also worked on text detection and recognition in images. I like to keep up to date with the latest techniques and results in the field, and then make the necessary adjustments to build a version that will work well for real problems at Facebook scale.
Before joining Facebook, I worked at two startups—one doing graph modeling for recruiting, the other working on vision for videos. Even earlier, I completed a BS in engineering physics and then an MSEE at Stanford.
Computer vision, including text detection and recognition, action recognition, object tracking, hierarchical classification and logo detection