Derek Hoiem
Professor of Computer Science at University of Illinois at Urbana-Champaign. Biggest past contributions are in single-view geometry and 3D scene understanding, object recognition and attribute-based representations, and multitask representation and learning.
My current research directions:
- XVG (miXed-View Geometry): How can we recover complete and precise 3D geometry for scenes viewed partly by multiple images and partly by single images? Our goal to develop a unifying framework for recognition-based single-view methods and correspondence-based multiview methods to produce compact, precise, complete, structured, and semantically rich 3D models.
- General Purpose Vision: How can we make vision systems that easily learn and adapt to new tasks and environments? Our goal is to reformulate visual learning as continual, opportunistically supervised, self-directed, and minimizing asymptotic error and sample complexity for unknown future tasks.
More can be found in my bio, my research group page, blog and the guide to the left (Home if you do not see it). Current students see my group page. Prospective students
see my Contact page. The group page is still under construction. Also see the CS@Illinois Computer Vision Group.
Current and former MS students
- Daeyun Shin, current
- Namtrata Prabhu, "Identifying facial landmarks, action units and emotions using deep networks", 2016
- Ka Wai Tsoi, "Improve OpenMVG and create a novel algorithm for novel view synthesis from point clouds", 2016
- Justin Thorsen, "Single-View Object Completion", 2014
- Pritam Sukumar, "Object Categorization using Collections of Parts and Second Order Pooling Features", 2013
- Sujay Bhobe, "Predicting Object Occupancy on the Floor from RGBD Images of Indoor Scenes", 2013
- Prateek Rungta, "Kinect Cloud Normals: Towards Surface Orientation Estimation", 2011
Current and former undergraduate students (incomplete)
- Naren Sivagnananadasan, current
- Daeyun Shin, 2015
- Junyoung Gwak, 2015
- Bryan Plummer, shadows and geometry recognition, 2013
- Johnston Jiaa, "Training and Evaluating Part Detectors with Human Input, 2013
- Keunhong Park, "Learning Analogies from Independent Part Models", 2013
- Brian Wang, "Hierarchical Histogram of Gradient Tree", 2013
- Chao Xia, "Compact Vision Inspection Platform", 2012
- Xing Li, Kinect sensors, 2012
- Doheum Park, "Web Cam Eye Gaze Estimation with Lighting Interaction", 2011
- Eun Ki, "Object Recognition", 2011
- Wei (Alex) Lou, senior thesis, "Cross-Category Based Object Pose Prediction", 2011
- Yodsawalai Chodpathumwan, RA, "Report on Factors Influencing Object Detection", 2011
- Brinda Gupta, attributes dataset collection, 2011
- Nive Suresh, attributes dataset collection, 2010
- Priya Dandawate, "Pose Recognition of Animals", 2010
- Arash Kahn, texture property recognition, 2010
- Jeff Chyan, honors project on animal pose classication, 2010
Funding
ONR MURI Award N00014-16-1-2007: "Understanding Scenes and Events through Joint Parsing, Cognitive Reasoning and Lifelong Learning" (2016-2020)
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 N000141010934:"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)
Home
