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.

Visit the G-Research Hub »

Share
  
Embed
  
Added: Over a year ago

To embed this video into your own website, copy and paste the code below.

More video from G-Research

G-Research Lecture with Professor Michael I. Jordan on Artificial Intelligence

The G-Research Lecture Series returns with this specially commissioned...

Watch videos from other companies...

BNP Paribas celebrates 150 years in the UK

A lot has happened since we came to the UK 150 years ago. But as Britain...

Grads go far

Looking to start your career working in a global organisation on world famous...

BriteCloud RF Countermeasure

BriteCloud Expendable Active Decoy (EAD) is a compact, DRFM-based active RF...

Hank Green on supporting trends for girls in STEM education

More and more girls are being encouraged to pursue careers in STEM, but...

Development at Newton

Seb, Magnus, Sarah and Jay tell us how they’re learning at Newton.

Show more +