In the vision lab at the University of Michigan we explore a number of critical problems in the area of computer vision. We focus on the analysis and modeling of visual scenes from static images as well as video sequences. Our research goals include: i) the semantic understanding of materials, objects, and actions within a scene; ii) modeling the spatial organization and layout of the scene and its behavior in time. The algorithms developed in our group enable the design of machines that can perform real-world visual tasks such as autonomous navigation, visual surveillance, or content-based image and video indexing.
Here are some highlights from our featured projects:
- Four papers (including two oral presentations) have been accepted to the upcoming CVPR 2013 conference - congratulations to W. Choi, Y. Chao, S. Bao, B. Kim, S. Xu, and R. Mittelman.
- Our work on collective activity recognition and tracking appeared in a recent press release and was featured in Communications of the ACM and other popular science portals.
- Prof. Silvio Savarese received the 2011 Best Paper Award from the Journal of Construction Engineering and Management. Click here for more details.
- Two papers have been accepted to the upcoming ECCV 2012 conference - congratulations to W. Choi (with an oral presentation), Y. Bao, and Y. Xiang.