A 2D + 3D Rich Data Approach to Scene Understanding: Jianxiong Xiao, MIT (IVC)
- Starts: 1:00 pm on Monday, February 11, 2013
- Ends: 2:00 pm on Monday, February 11, 2013
Abstract: Recently, researchers have come to realize that big data is critical for building scene-understanding systems that can recognize the semantics and reconstruct its 3D structure. In this talk, I will share my experience in leveraging big data for scene understanding, including my work on constructing the SUN Database, which is now the standard dataset for scene recognition, and my work in building large-scale 3D models for scene reconstruction. Although these two tasks in scene understanding ‒ recognition and reconstruction ‒ are highly related, traditionally they have been studied separately. As a result, the current approaches represent space as isolated, view-based snapshots that do not have an integrated spatial representation. To address these issues, we construct a "place-centric" representation that allows us to understand full 3D scenes. This new kind of 2D + 3D scene understanding opens up exciting new opportunities, and also raises many challenges in data analysis and rich representations. Bio: Jianxiong Xiao is a Ph.D. candidate in the Computer Science and Artificial Intelligence Laboratory (CSAIL) at Massachusetts Institute of Technology (MIT). Before that, he received a B.Eng. and a M.Phil. from the Hong Kong University of Science and Technology. His research interests are in computer vision, with a focus on scene understanding. His work has received the Best Student Paper Award at the European Conference on Computer Vision (ECCV) in 2012, and appeared in popular press. Jianxiong was awarded the Google U.S./Canada Ph.D. Fellowship in Computer Vision in 2012 and MIT CSW Best Research Award in 2011. More information can be found on his website: http://mit.edu/jxiao.
- MCS 148