Statistical problems in computer vision

Duration: 13 mins 10 secs

Share this media item:

Embed this media item:

<iframe width="_width_" height="_height_" src="https://sms.cam.ac.uk/media/1178214/embed" frameborder="0" scrolling="no" allowfullscreen></iframe>

Choose size:

About this item

Available Formats

About this item

Statistical problems in computer vision's image

Description:	Nowozin, S (Microsoft) Monday 26 September 2011, 16:25-16:35


Created:	2011-10-04 11:00
Collection:	Design and Analysis of Experiments Cambridge Statistics Initiative 2011
Publisher:	Isaac Newton Institute
Copyright:	Nowozin, S
Language:	eng (English)


Abstract:	Computer vision is one of the many fields that successfully adopted machine learning for building predictive models. Yet, despite their success some of the fields' most popularly used models such as conditional random fields remain poorly understood theoretically and require approximations to be practical. I discuss a few of open theoretical and practical questions in these models in the computer vision context.

Abstract:

Computer vision is one of the many fields that successfully adopted machine learning for building predictive models. Yet, despite their success some of the fields' most popularly used models such as conditional random fields remain poorly understood theoretically and require approximations to be practical. I discuss a few of open theoretical and practical questions in these models in the computer vision context.

Available Formats

Format	Quality	Bitrate	Size
MPEG-4 Video	640x360	1.85 Mbits/sec	182.71 MB	View	Download
WebM	640x360	655.46 kbits/sec	62.97 MB	View	Download
Flash Video	484x272	569.32 kbits/sec	54.90 MB	View	Download
iPod Video	480x270	506.35 kbits/sec	48.89 MB	View	Download
MP3	44100 Hz	125.03 kbits/sec	11.87 MB	Listen	Download
Auto *	(Allows browser to choose a format it supports)