G-Research & The Alan Turing Institute presents: Machines That See

A lecture given by Research Director for the Alan Turing Institute and former Laboratory Director of Microsoft Research (Cambridge), Prof. Andrew Blake: The visible world is ambiguous, so estimating physical properties by machine vision relies on probabilistic methods. Prior distributions over shape can help significantly to make finding and tracking objects more robust. Learned distributions for colour and texture make the estimators even more discriminative. These ideas fit into a philosophy of vision as inference: exploring hypotheses for the contents of a scene that explain an image as fully as possible.

Share
Embed
Share
×
Copy the URL...
Or share on...
Embed
×
To embed this video into your own website, copy and paste the code below.
Follow your favourite employers
Save jobs to your shortlist
Receive personalised alerts
Access our live webinars
Register now
On the move? Download The App
Gradcracker Logo
Gradcracker Limited, October House, Long Street, Easingwold, York, YO61 3HX
01347 823822 | info@gradcracker.com | Company registration number: 6370348
© 2007 - 2024 Gradcracker Limited
Gradcracker and Cookies
We use cookies to ensure that we give you the best experience on our website.
If you continue we'll assume that you are happy to receive all cookies from Gradcracker.
Continue
Learn more