1950 University Ave, Suite 200
Berkeley, California 94704

(Free and open to the public - and followed at 4pm with a Social Jam that includes refreshments - and beer. It would be helpful if you mark attending/watching above).

Exploiting the Link Between Words and Pictures

There are billions of photographs with associated text available on the web. Some common areas where images and words are naturally linked include: web pages, captioned photographs, and video with speech or closed captioning. The central challenge that needs to be solved in order to organize these collections effectively is how to extract images in which specified objects are depicted from large pools of pictures with noisy text. This is a very difficult problem because the relationship between words associated with an image and objects depicted within the image is often complex.

My work has demonstrated that for many situations these collections can be mined successfully. I will talk about three projects that I have worked on in this area:

Automatically labeling faces in news photographs, classifying images from the web, and ranking iconic images from consumer photo collections. All papers, created datasets, and demos are available on my webpage at: http://www.cs.berkeley.edu/~millert/.

Tamara Berg is a Postdoctoral Fellow at Yahoo! Research Berkeley. Her research straddles the boundary between Computer Vision and Natural Language Processing.

Before coming to Yahoo!, Tamara was a graduate student at the University of California Berkeley and she will be receiving her PhD from there in May of 2007.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Recent Successes and Failures of Recognition Algorithms in Computer Vision

Recognition algorithms in computer vision have come a long way in the last 10 years. I will describe some of the successes and failures for recognition algorithms, concentrating on some of our work at Berkeley including:

- recognizing objects by matching shapes in images
- recognizing actions in video
- recognizing scenes
- indexing large collections of video by content

The talk will cover what might be the short-term future of recognition algorithms and applications.

Alexander Berg is a post-doctoral fellow at Yahoo! Research in Berkeley, California, and a visiting scholar at the University of California, Berkeley. Alex earned a Ph.D. in Computer Science at U.C. Berkeley, and a MA and BA in Mathematics at Johns Hopkins University. His work concentrates on recognition from visual data. More information can be found at http://www.cs.berkeley.edu/~aberg

- - -
Yahoo! Research Berkeley's Brain Jam is an "almost weekly" speaker series on topics related to media, social media, mobile media, media annotation, and the leftist media. Well, maybe not the last one. To join our mailing list, please visit: http://groups.yahoo.com/group/yrb-bj

Official Website: http://whyrb.com

Added by berkeleybohemian on February 14, 2007