Assistant Professor
Joined School 2010
BSc (McGill University),
MSc (University of British Columbia),
PhD (University of British Columbia)
| jhoey@uwaterloo.ca | |
| Web | http://www.cs.uwaterloo.ca/~jhoey/ |
| Voice | 37744 |
| Fax | 519-885-1208 |
|
| Jesse Hoey
Assistant Professor Joined School 2010 BSc (McGill University),
|
Professor Hoey works on three aspects of artificial intelligence. First, he works on decision theory, particularly in Markov decision processes (MDPs), and their partially observable counterparts, POMDPs. He is interested in learning these models from data, and on solving them, particularly in large state and observation spaces. Second, he works on computer vision, and specifically on the recognition of human behaviour (including gesture, facial expression and gait/body posture) from dynamic video scenes. He is interested in task-oriented computer vision, in which the goal is to optimise over the action/policy space for an automated agent rather than over the state space as in traditional computer vision (e.g. in the recognition of objects/behaviours for their sake alone). Third, he works on applications of computer vision and decision theory in building assistive systems for persons with physical and cognitive disabilities. In particular, he is interested in systems that help a person with dementia doing activities of daily living (ADL) using cameras and other sensors to inform decision processes with multiple and competing objectives.
Professor Hoey's research is funded in part by the American Alzheimer's Association and the Leverhulme Trust. He collaborates closely with researchers in Canada (Toronto), the UK (Newcastle, Dundee, Belfast,Heriot-Watt,Edinburgh), Germany (Bielefeld), and Mexico (Puebla, Cuernevaca, Ensenada). His recent projects include a camera-based system to help persons with dementia during handwashing, a tangible (multi-touch) device for art therapists, and a haptic robotic device for stroke rehabilitation. His most recently funded project is a collaboration with researchers in Mexico to develop socially aware ambient displays that help with communication and situation awareness for persons with dementia.
Microsoft/AAAI Distinguished Contribution Award, IJCAI Workshop on Assisted Cognition (2009); Best Paper Award, International Conference on Computer Vision Systems (2007); Canesta Computer Vision Contest Grand Prize Winner (2006); Horace Watson Medal, McGill University Physics (1992)
Professor Hoey spent four years in Scotland as an Assistant Professor in the School of Computing at the University of Dundee. He is also an adjunct scientist at the Toronto Rehabilitation Institute, where he works on assistive technology projects in collaboration with the Intelligent Assistive Technologies and Systems Lab (IATSL).
Mihailidis, Alex and Blunsden, Scott and Boger, Jennifer and Richards, Brandi and Zutis, Krists and Young, Laurel and Hoey, Jesse. Towards the Development of a Technology for Art Therapy and Dementia: Definition of Needs and Design Constraints. The Arts in Psychotherapy, 2010.
Hoey, Jesse and Poupart, Pascal and von Bertoldi, Axel and Craig, Tammy and Boutilier, Craig and Mihailidis, Alex. Automated Handwashing Assistance for Persons with Dementia Using video and a Partially Observable Markov Decision Process. Computer Vision and Image Understanding, 114(5):503-519, 2010.
Mihailidis, Alex and Boger, Jen and Candido, Marcelle and Hoey, Jesse. The COACH prompting system to assist older adults with dementia through handwashing: An efficacy study. BMC Geriatrics, 8(28)2008.
Hoey, Jesse and von Bertoldi, Axel and Poupart, Pascal and Mihailidis, Alex. Assisting Persons with Dementia during Handwashing Using a Partially Observable Markov Decision Process. Proceedings of the International Conference on Vision Systems, 2007.
Hoey, Jesse and Little, James J.. Value-Directed Human Behavior Analysis from Video Using Partially Observable Markov Decision Processes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(7):1118-1132, 2007.
Poupart, Pascal and Vlassis, Nikos and Hoey, Jesse and Regan, Kevin. An Analytic Solution to Discrete Bayesian Reinforcement Learning. Proceedings of the 23rd International Conference on Machine Learning (ICML), 2006.
Hoey, Jesse and Poupart, Pascal. Solving POMDPs with Continuous or Large Discrete Observation Spaces. Proc. International. Joint Conference on Artificial Intelligence, pp. 1332-1338, 2005.
Hoey, Jesse and Little, James J.. Decision Theoretic Modeling of Human Facial Displays. Proc. European Conference on Computer Vision, 2004.
Hoey, Jesse and St-Aubin, Robert and Hu, Alan and Boutilier, Craig. SPUDD: Stochastic Planning using Decision Diagrams. Proceedings of Uncertainty in Artificial Intelligence, pp. 279-288, 1999.
David R. Cheriton School of Computer Science
University of Waterloo
Waterloo, Ontario, Canada N2L 3G1
Tel: 519-888-4567 x33293
Fax: 519-885-1208
Contact | Feedback: cs-webmaster@cs.uwaterloo.ca | David R. Cheriton School of Computer Science | Faculty of Mathematics
Last modified: Monday, 20-Dec-2010 14:29:53 EST
