RESEARCH
Professor Learned-Miller's interests can be broadly categorized as applying ideas and methods from machine learning to problems in computer vision. His research has included work on the following problems: learning from one example (one-shot learning), face recognition and face detection, segmentation of moving objects in video, algorithms for the joint alignment of unlabeled images, and text recognition. He has produced some of the most widely used benchmarks in face recognition research, including Labeled Faces in the Wild and the Face Detection Database and Benchmark. His current work focuses on unsupervised, self-supervised, and semi-supervised learning, and on mechanisms for regulating face recognition technology.