Scene Discovery by Matrix Factorization

Loeff, Nicolas; Farhadi, Ali; Forsyth, David A.

Permalink

https://hdl.handle.net/2142/11420 Copy

Description

Title

Scene Discovery by Matrix Factorization

Author(s)

• Loeff, Nicolas
• Farhadi, Ali
• Forsyth, David A.

Issue Date

2008-01

Keyword(s)

• computer animation
• computer graphics

Abstract

What constitutes a scene? Defining a meaningful vocabulary for scene discovery is a challenging problem that has important consequences for object recognition. We consider scenes to depict correlated objects and present visual similarity. We introduce a max-margin factorization model that finds a low dimensional sub-space with high discriminative power for correlated annotations. We postulate this space should allow us to discover a large number of scenes in unsupervised data; we show scene discrimination results on par with supervised approaches. This model also produces state of the art word prediction results including good annotation completion.

Type of Resource

text

Permalink

http://hdl.handle.net/2142/11420

Copyright and License Information

You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the University of Illinois at Urbana-Champaign Computer Science Department under terms that include this permission. All other rights are reserved by the author(s).

Owning Collections