![]() |
COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
University of Cambridge > Talks.cam > Microsoft Research Cambridge, public talks > Structured Prediction Models for High-level Computer Vision Tasks
![]() Structured Prediction Models for High-level Computer Vision TasksAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins. This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending Rich statistical models have revolutionized computer vision research: graphical models and structured prediction in particular are now commonly used tools to address hard computer vision problems. I discuss what distinguishes these computer vision problems from other machine learning problems and how this poses unique challenges. I argue that most computer vision models are misspecified and discuss the consequences of popular estimators in this case, concluding that we either have to use non-parametric models or use estimators robust to misspecification. As one possible solution, I propose a novel discrete random field model applicable to a large number of computer vision tasks. The model is conditionally specified, non-parametric, and able to represent complex label interactions, yet it can be trained from hundreds of images in minutes on a single machine. This talk is part of the Microsoft Research Cambridge, public talks series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsLiberia's Independence Day Talk CamBridgeSens Global Student Education Forum (GSEF) Talk SeriesOther talksMicrosporidia: diverse, opportunistic and pervasive pathogens On the climate change conversation Magnetic microscopy of meteorites: probing the magnetic state of the early solar system Replication or exploration? Sequential design for stochastic simulation experiments Highly Energy Efficient Key-value Store for In-network Computing Mechanical performance of wall structures in 3D printing processes: theory, design tools and experiments |