Computer Science and Engineering

AI Seminar

From Recognition to Reasoning

Justin JohnsonAssistant ProfessorComputer Science and Engineering, University of Michigan
3725 Beyster BuildingMap


In recent years deep learning systems have become proficient at recognition problems: for example we can build systems that can recognize objects in images with high accuracy. But recognition is only the first step toward intelligent behavior. I am interested in solving problems that move from recognition to reasoning: systems should be able not only to recognize, but also to perform higher-level tasks based on what they perceive. I will showcase two projects that aim to jointly recognize and reason using end-to-end deep learning systems: Mesh R-CNN, in which we jointly detect objects and predict 3D triangle meshes; and PHYRE, a new benchmark for physical reasoning.



Justin Johnson is an Assistant Professor of Computer Science and Engineering at the University of Michigan, Ann Arbor and a Visiting Scientist at Facebook AI Research. He completed his PhD at Stanford University, advised by Fei-Fei Li. His research interests lie primarily in computer vision and include visual reasoning, image synthesis, and 3D perception.


AI Lab