Derek Hoiem

Derek Hoiem

I'm an associate professor of Computer Science at University of Illinois at Urbana-Champaign (UIUC). My main interest is in general visual scene understanding. Scene understanding is the ability to infer general principles and current situations in a way that helps to achieve goals. So far, much progress has been made by breaking down vision into a set of narrowly defined tasks and tackling them as independent pattern matching or image processing problems. I want to think of vision in terms of real-world space, surfaces, objects, and relations. I also want to develop frameworks that allow visual knowledge to be accumulated, so that each task contributes to a worldview that makes learning new tasks easier. My past includes a Postgraduate Beckman Fellowship at UIUC, Ph.D. at the Robotics Institute at CMU with Alyosha Efros and Martial Hebert, and collaborations at Intel Research Pittsburgh and Microsoft Research Cambridge. See my bio for more details.

My research follows three main themes:

Use the guide to the left to find publications, projects, software, and presentations (click Home if you do not see the links). Prospective students can find related info in the Contact page.

PhD Student Advisees and Collaborators

Qieyun Dai
Kevin Shih
Saurabh Singh

Joseph Degol

Jason Rock

Chuhang Zou

Tanmay Gupta

Zhizhong Li

Former PhD Students and Collaborators

Also see the Computer Vision Group webpage.

Current and former MS students

Current and former undergraduate students (incomplete)


ONR MURI Award: "Understanding Scenes and Events through Joint Parsing, Cognitive Reasoning and Lifelong Learning" (2015-2019)
NSF Award 14-46765: "Autonomous Vision Based Construction Progress Monitoring and Activity Analysis for Building and Infrastructure Projects" (2015-2018)
NSF Award 14-21521: "Recovering Object 3D Shape and Material from Isolated Images" (2014-2016)
Sloan Fellowship (2013-2014)
Intel Early Career Faculty Award (2012)
Gift from Intel (2011)
Gifts from Microsoft (2009, 2010)
NSF Award 10-53768: "CAREER: Large-Scale Recognition using Shared Structures, Flexible Learning, and Efficient Search" (2011-2015)
ONR MURI Award:"Rich Representations with Exposed Semantics for Deep Visual Reasonings" (2010-2015)
NSF Award 09-04209: "Physically Grounded Object Recognition" (2009-2013)
NSF Award 09-16014: "Exploiting Geometric and Illumination Context in Indoor Scenes" (2009-2012)
Google Research Award: "Describing Objects by their Attributes from Images" (2009-2010)