Learning in Computer Vision

author: Simon Lucey, Carnegie Mellon University
published: May 5, 2008,   recorded: March 2008,   views: 53038
Categories

Slides

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.
  Delicious Bibliography

 Watch videos:   (click on thumbnail to launch)

Watch Part 1
Part 1 1:02:02
!NOW PLAYING
Watch Part 2
Part 2 52:43
!NOW PLAYING
Watch Part 3
Part 3 56:26
!NOW PLAYING
Watch Part 4
Part 4 57:18
!NOW PLAYING
Watch Part 5
Part 5 32:11
!NOW PLAYING
Watch Part 6
Part 6 25:01
!NOW PLAYING
Watch Part 7
Part 7 45:36
!NOW PLAYING

Description

This tutorial he will cover some of the core fundamentals in vision and demonstrate how they can be interpreted in terms of machine learning fundamentals. Unbeknownst to most researchers in the field of machine learning, the fundamentals of object registration and tracking such as optical flow, interest descriptors (e.g., SIFT), segmentation and correlation filters are inherently related to the learning topics of regression, regularization, graphical models, generative models and discriminative models. As a result many aspects of vision can be interpreted as applied forms of learning. From this discussion on fundamentals we shall also explore advanced topics in object registration and tracking such as non-rigid object alignment/ tracking and non-rigid structure from motion and how the application of machine learning is continuing to improve these technologies.

See Also:

Download slides icon Download slides: mlss08au_lucey_linv.pdf (35.0 MB)


Help icon Streaming Video Help

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 Dio, May 27, 2008 at 6:24 p.m.:

you can check the implementation of the compositional warps by following this link: http://www.codeproject.com/KB/recipes...


Comment2 Rohan, January 10, 2009 at 3:48 p.m.:

Amazing Lecture.
Really Easy to understand..
Easily the best Computer Vision - Detection and Tracking lecture that i have seen.
He explains it in really intuitive way!

3 Main Things to look at when doing CV
"Registration. registration, registration"

Thank you for these lectures


Comment3 Asa Hartley, July 3, 2010 at 5:38 p.m.:

Sounds like this dude is umm... talking out his umm.. arse. He's probably from like umm.. Toowoomba or something.

:P <3


Comment4 Davor (staff), July 13, 2010 at 4:10 p.m.:

Dear Asa Hartley, please mind your language! You are offending our whole community, your comments are not helping anyone, they are not constructive and very disrespectful. If you have a technical problem you can drop us an email at [email protected] or a ticket, if you have a problem with the author you can send him a private email.


Comment5 Asa Hartley, July 15, 2010 at 12:54 a.m.:

LOL way to over-react Davor. For someone involved in a technology teaching website you fail at the internet.

If you will note the use of the ':P' and '<3' emoticons you would realise this was indeed a friendly jibe and not meant as disrespect. As it so happens I went to high school with Simon and we are quite good friends.

I'm also quite sure your "whole community" isn't going to be terribly perturbed by my one single use of one of the tamest profanities in the world today. In fact,where I am from it is considered a common part of the vernacular.

But for your sake I shall refrain from using my harmless profanity, if you'll kindly take the pole out of yours ;)

Write your own review or comment:

make sure you have javascript enabled or clear this field: