This year program is available here .

I have 10,000 photos of my five-year-old son. This number, while it sounds large, is actually very common--most of us have many thousands of photos of family and friends. These photos track the changes in my son's appearance, shape, and behavior over the course of his life. They contain detailed information about shape geometry and reflectance, and it's evolution over time. They also characterize the variability in his facial expressions. Can we reconstruct my son from this collection (and what does that mean exactly?). In this talk, I explore new directions in photo browsing and modeling from large photo collections of people.

Steve Seitz is a Professor in the Department of Computer Science and Engineering at the University of Washington. He received his B.A. in computer science and mathematics at the University of California, Berkeley in 1991 and his Ph.D. in computer sciences at the University of Wisconsin, Madison in 1997. Following his doctoral work, he spent one year visiting the Vision Technology Group at Microsoft Research, and subsequently two years as an Assistant Professor in the Robotics Institute at Carnegie Mellon University. He joined the faculty at the University of Washington in July 2000. He was twice awarded the David Marr Prize for the best paper at the International Conference of Computer Vision, and has received an NSF Career Award, an ONR Young Investigator Award, and an Alfred P. Sloan Fellowship.
Professor Seitz is interested in problems in computer vision and computer graphics. His current research focuses on capturing the structure, appearance, and behavior of the real world from digital imagery. He enjoys biking, hiking, eating crab, and staring obsessively at Mount Rainier.

Since 1986, IEEE has sponsored workshops on understanding motion from video imagery, but only in the last several years has the acquisition of very high quality video data been so easy to scale to consumer devices, aerial platforms, and large-scale camera networks. Hence there is a growing demand of algorithms to automatically analyze and interpret these video data. Additionally there is an increasing need for scalable algorithms to allow processing of the enormous data volumes captured.

We encourage high-quality original submissions in any area of video processing and motion interpretation including:

• Multi-sensor and multi-target detection and tracking
• Extraction of semantics from video
• Human activity recognition
• Gesture and gait analysis and recognition
• Low-level motion analysis (Optic flow, motion segmentation, structure from motion)
• Analysis of video data from novel sensors
• Performance evaluation of video understanding systems
• Activity modeling and recognition
• Video retrieval
• Video for surveillance and biometrics
• Video event detection and recognition
• Modeling from video- or photo-collections

This year we particularly encourage submissions that tackle large-scale problems in areas such as community photo-collections or distributed camera networks.

This year, the motion workshop (WMVC) will function as an embedded track within the Workshop on Applications of Computer Vision (WACV). The workshop will have 6-page papers, which may be presented as either oral or poster presentations (extra pages will be $100 a page, up to an 8-page maximum). The venue will be the Sheraton Keauhou Bay (Hawaii). The WMVC proceedings will be published electronically on a conference CD-ROM and on IEEExplore.

• Pierre Fite-Georgel - UNC Chapel Hill, USA
• Jan-Michael Frahm - UNC Chapel Hill, USA
• Nathan Jacobs - University of Kentucky, USA

• Paper submission: September 6, 2010 (1:00 PM PT)
• Paper decisions: October 10, 2010
• Camera-ready: November 1, 2010
• Workshop: January 6, 2011