RI | People | Stella Yu

Text only version of this site

Stella Yu
PhD Student

No longer a member of RI.

For more information, see my personal homepage.

Jump to: Research interests | Keywords | Labs & Groups | Publications

Research interests

I am a member of the CNBC Active Perception Laboratory.

I am interested in the computational modeling of perceptual organization, in order to better understand the visual perception as well as developing better machine vision algorithms. I am currently working on image segmentation incorporating low level to high level cues.

Research interest keywords

active perception, biological vision, computer vision, and machine learning

Past Labs & Groups

Human Identification at a Distance - We are developing and evaluating human identification technologies as part of the Defense Advanced Research Projects Agency (DARPA) sponsored program in Human Identification at a Distance (HumanID).

Microdynamic Systems Laboratory - Exploring the limits of robotics in terms of speed, precision, dexterity and miniaturization.

Recent publications [View all 11 publications]

• Computational Models of Perceptual Organization
  S. Yu
  doctoral dissertation, tech. report CMU-RI-TR-03-14, Robotics Institute, Carnegie Mellon University, May, 2003. [Abstract]
  Download: pdf [3763 KB], ps.gz [7912 KB] copyrighted

• Concurrent Object Segmentation and Recognition with Graph Partitioning
  S. Yu, R. Gross, and J. Shi
  Proceedings of Neural Information Processing Systems (NIPS '02), November, 2002. [Abstract]
  Download: pdf [680 KB] copyrighted

• Understanding Popout through Repulsion
  S. Yu and J. Shi
  Computer Vision and Pattern Recognition, December, 2001. [Abstract]
  Download: pdf [428 KB] copyrighted

• A Hierarchical Markov Random Field Model for Figure-ground Segregation
  S. Yu, T.S. Lee, and T. Kanade
  Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition ( EMMCVPR'01 ), September, 2001. [Abstract]
  Download: pdf [451 KB] copyrighted

• Grouping with Directed Relationships
  S. Yu and J. Shi
  Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition ( EMMCVPR'01 ),, September, 2001. [Abstract]
  Download: pdf [608 KB] copyrighted

• Grouping with Bias
  S. Yu and J. Shi
  tech. report CMU-RI-TR-01-22, Robotics Institute, Carnegie Mellon University, July, 2001. [Abstract]
  Download: pdf [472 KB] copyrighted

• Perceiving Shapes through Region and Boundary Interaction
  S. Yu and J. Shi
  tech. report CMU-RI-TR-01-21, Robotics Institute, Carnegie Mellon University, July, 2001. [Abstract]
  Download: pdf [460 KB] copyrighted

• Segmentation with Pairwise Attraction and Repulsion
  S. Yu and J. Shi
  Proceedings of the 8th IEEE IInternational Conference on Computer Vision (ICCV'01), Vancouver, British Columbia, July, 2001. [Abstract]
  Download: pdf [513 KB] copyrighted

• Understanding Popout: Pre-attentive Segmentation through Nondirectional Repulsion
  S. Yu and J. Shi
  tech. report CMU-RI-TR-01-20, Robotics Institute, Carnegie Mellon University, July, 2001. [Abstract]
  Download: pdf [477 KB] copyrighted

• An Information-Theoretic Framework for Understanding Saccadic Behaviors
  T.S. Lee and S. Yu
  Advance in Neural Information Processing Systems, MIT Press, Vol. 12, 2000. [Abstract]
  Download: pdf [373 KB] copyrighted