University of Cambridge > Talks.cam > Inference Group > Epitomic representation of natural signals

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Epitomic representation of natural signals

Download to your calendar using vCal

If you have a question about this talk, please contact Phil Cowans .

Many natural signals such as images, audio and genetic sequences have repeating fragments that can be compactly expressed using, what we call as, an epitome. An epitome of a signal is its compact representation that is learned using overlapping segments or patches of various sizes from the signal. In this talk, I will explain a generative model for images using epitomes. When the epitomic representation is used in a hierarchical generative model of image formation, appropriate inference algorithms can be derived to extract epitomes from a single image or a collection of images and simultaneously perform various tasks such as image segmentation, motion estimation, super-resolution and image denoising. Time permitting, I will preview recent work by colleagues on extending this to videos.

Joint work with Nebojsa Jojic (Microsoft Research) and Brendan Frey (University of Toronto)

This talk is part of the Inference Group series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Winstanley Lecture Hall, Trinity College (online map @ http://www.acs-cam.org.uk/CRSS/venue/venue_CRSS.html) T001, Austin Building Cripps Meeting Room 3, Magdalene College

Other talks

Rothschild Public Lecture: The Quantum Centenary: from Order to Chaos Title to be confirmed Title to be confirmed Am I a Member? Auditing Private Machine Learning Title to be confirmed BSU Seminar: "Response Adaptivity Across Clinical Trials In Portfolios of Biomedical Innovations"
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity