13 Feb
Wednesday, 02/13/2013 11:00am to 12:00pm

Alex Berg
Stony Brook University
Department of Computer Science

Computer Science Building, Room 151

Faculty Host: Erik Learned-Miller


Recognition in computer vision is beginning to work, making the next question, "What should we recognize?" Some of my work has explored increasing the label space for recognition toward large numbers of semantic labels embedded in a hierarchy, toward multiple attribute labels, and toward detailed spatial parsing. Predictions of these labels are improving results on problems from face recognition to large scale similar image retrieval and building stronger connections between computer vision and natural language processing. At the same time, this move toward BIVISION requires that we meet the unavoidable computational challenges in the underlying machine learning problems. I will present some results in each of these directions and try to motivate some of the wide open problems in this area.


Alex Berg's research concerns computational visual recognition. He has worked on general object recognition in images, action recognition in video, human pose identification in images, image parsing, face recognition, image search, and machine learning for computer vision. He co-organizes the ImageNet Large Scale Visual Recognition Challenge, and organized the Large Scale Learning for Vision workshop in 2011. He is currently an assistant professor in computer science at Stony Brook University. Prior to that he was a research scientist at Columbia University and Yahoo! Research. His PhD at U.C. Berkeley developed a novel approach to deformable template matching. He earned a BA and MA in Mathematics from Johns Hopkins University and learned to race sailboats at SSA in Annapolis.

A reception will be held at 3:40 in the atrium, outside the presentation room.