App2You Got Scobalized!

App2You the computer science startup from Jacobs School professor and database guru Yannis Papakonstantinou set up the online submission and review system for the approximately 1,000 companies that are submitting themselves for a spot on the next TechCrunch 50 List.

Robert Scoble highlighted this fact on his Twitter stream this week:


"App2You made the site that 1,000 companies entered their data into and managed the process behind the scenes of TC50.

03:41 PM September 10, 2008 from web"

Scoble rose to prominence as a revolutionary blogger for Microsoft. He is currently a video blogger for Fast Company and runs the popular Scobalizer blog.

The Animated Hair is Blowing in the Wind

Though the song says that "the answer my friend is blowing in the wind," UC San Diego computer scientists and graphics researchers are part of a group that has found the answer for getting hair on animated characters to blow in the wind.

They presented their findings last week at SIGGRAPH 2008, the most prestigous academic computer graphics conference. The work is a collaboration between researchers at UC San Diego, Adobe Inc, and MIT.

Discover Magazine ran a nice story about this work.

Here is the caption for the image at the top of this post:
The left two images demonstrate different aspects of a real hairstyle that the computer scientists captured. The third image from left is the reference photograph of the real hairstyle. The new algorithms created the image on the right, which has photorealistic highlights and texture, even through there are no photographs that were taken at that angle.

Computer Science Collaborator

Pieter Dorrestein, one of computer science professor Pavel Pevzner's collaborators here at UC San Diego, was featured in a short profile in The Scientist. Dorrestein and Pevzner devised a way to cut the time it takes to determine the structure of peptides derived from natural compounds from six months or a year to as little as one day. This advance may assist drug discovery researchers – who need to know as much as possible as quickly as possible about the natural products with antibiotic, antiviral and other pharmacologically interesting properties that they are probing.

They presented the work RECOMB 2008 (Research in Computational Molecular Biology) on March 31 in Singapore.

Taaz.com video from CBS

San Diego's CBS affiliate KFMB Channel 8 created a great two minute video on, Taaz.com, the virtual makeover Web site started by computer science professor David Kriegman.

Check out the entertaining video here or
http://www.cbs8.com/features/special_assignment/story.php?id=137476#

Flash Server and Nature paper

The press release for a Nature paper from the bioengineering lab of Jeff Hasty includes an embedded video of growing yeast cells (cooler than it sounds) that is streaming on our new flash server. This is the first press release video to stream from our flashy new flash server. We are hoping this is going to be a cross-platform solution to our video needs. Check it out!



http://www.jacobsschool.ucsd.edu/news/news_releases/release.sfe?id=760

Remote Control Face in Voice of San Diego

The Voice of San Diego ran a great story on Jacob Whitehill's computer science research. Whitehill is the guy who can turn his face into a remote control, thanks to a Web cam and some serious computer science can do. The story is by Darryn Bennett.


Voice of San Diego, July 29 -- A third year computer science graduate student at UCSD, Jacob Whitehill and his colleagues are working to make a new generation of robots that would be effective and responsive teachers. They believe the key is to train them to recognize and respond to facial expressions, the way humans do naturally. Whitehill described the demonstration, part of his research at UCSD's Machine Perception Laboratory, as "almost like having a remote control built into your face."

Label Reading with a Purpose

The Calit2 Life blog ran a great story from Jacobs School computer science professor Serge Belongie. The post is republished below. This is an update on a story that I wrote about last fall, when Belongie and his collaborators presented their ideas at a conference.

Soylent Grid Is People!

One of the big challenges in solving large scale object recognition problems is the need to obtain vast amounts of labeled training data. Such data is essential for training computer vision systems based on statistical pattern recognition techniques, for which a single example image of an object is unfortunately not enough.

For my research group, this has been especially evident in our work on the Calit2 GroZi project, which has the goal of developing assistive technology for the visually impaired. This includes tasks such as recognizing products on grocery shelves and reading text in natural scenes. (Check out this YouTube video for a bit of background on the project.)
In the past, this type of labor-intensive data labeling task would fall on hapless grad students or undergrad volunteers. (As an example, last winter my TIES group and CSE graduate student Shiaokai Wang manually labeled all the text on hundreds of product packages, all for the meager reward of pizza and soda.)
Recently, however, a movement has emerged that harnesses Human Computation to solve such labeling tasks using a highly distributed network of human volunteers. As an example, CMU's recaptcha system applies this principle to the task of transcribing old scanned documents, wherein the image quality is low enough to throw off conventional Optical Character Recognition (OCR) software.
Think of it like this. Every time you solve a CAPTCHA, i.e., those distorted words you have to type in at websites like myspace and hotmail to prove that you're not a spambot, you're using your powerful human intelligence to solve a small puzzle. Systems like recaptcha, the Mechanical Turk, and the Soylent Grid (currently under development by Calit2 affiliate Stephan Steinbach, CSE graduate student and CISA3 project member Vincent Rabaud, visiting scholar Valentin Leonardi, and TIES summer scholar and ECE undergraduate Hourieh Fakourfar) seek to redirect this human problem-solving ability toward useful tasks.
Hourieh's summer project has as its aim to adapt our fledgling Soylent Grid prototype to the above-mentioned text annotation task. A critical requirement for such a system to work is a steady traffic of web visitors looking for content.

Some day, when the Soylent Grid is a household name, we'll have strategic partnerships set up with big-name websites that serve up 1000s of CAPTCHAs per hour. Until then, we've got our work cut out for us to find some traffic to get our experiment started. As a humble starting point, we're going to outfit the pdf links on my group's publications page so that people who click on the link get served a labeling task before they can download the pdf. From there, we plan to move on to bigger and better websites with increased levels of traffic.
Now you may ask, how do we prevent visitors from inputting nonsense instead of providing useful annotation? As with recaptcha, the solution is to use a pair of images, one with known (ground truth) annotation, the other unknown. In this way, the visitor's response on the known example can be used to validate the response on the other example. Moreover, the response of multiple visitors on the same image can be pooled to form confidence levels, and when this level is high enough, an image can be moved from the "unknown" stack to the "known" stack.
Naturally, many questions remain. How do we make these labeling tasks sufficiently atomic and easy to complete so that the web visitor doesn't get frustrated? How much ground truth labeling is needed in a given image database to "prime the pump"? How do we deal with ambiguity in the labeling task or in the user input? Some initial thoughts on these and other questions are put forward in Stephan and Vincent's position paper from ICV'07, but there's nothing like a messy real-world experiment to get real-world answers to these questions!