ABSTRACT
In this talk I will provide an overview of my group’s research projects at Cornell Tech involving Computer Vision, Machine Learning, and Human-in-the-Loop Computing. I will cover projects involving identification of plant and animal species (Visipedia) and learning perceptual embeddings of food (SNaCK). I will conclude with a preview of a new effort to build a projector-based, human-computer interaction apparatus that allows computers to point to physical objects in the real world (PointAR).