Marshall Tappen

About Me


I am currently a Research Scientist at Amazon.com. Until December 2013, I was a tenured associate professor of computer science at the University of Central Florida

I received my PhD from MIT in 2006, SM from MIT in 2002, and BS from Brigham Young University in 2000.

I have also worked as a data scientist at Row Sham Bow, which is developing some very exciting analytics technologies for online games.

Email: mtappen at cs.ucf.edu

Publications

2013

B. Liu, F. Sadeghi, M. F. Tappen, C. Liu, and O. Shamir. Probabilistic Label Trees for Efficient Large Scale Image Classification To appear in The 2013 IEEE Conference on Computer Vision and Pattern Recognition(CVPR) [PDF]

Z. Han, S. Z. Masood, J. Hochreiter, S. Fonte, and M. F. Tappen Album-Oriented Face Recognition For Online Social Networks To Appear in the 10th IEEE International Conference on Automatic Face and Gesture Recognition [PDF]

2012

F. Sadeghi and M. F. Tappen Latent Pyramidal Regions for Recognizing Scenes To Appear in The 2012 European Conference on Computer Vision [PDF]

M. F. Tappen and C. Liu A Bayesian Approach to Alignment-based Image Hallucination To Appear in The 2012 European Conference on Computer Vision [PDF]

C. Ellis, S. Masood, M. F. Tappen, J. J. LaViola, and R. Sukthankar, Exploring the Trade-off Between Accuracy and Observational Latency in Action Recognition, To Appear in the International Journal of Computer Vision [PDF] Slides overviewing this project [PDF]

Jian Sun and Marshall F. Tappen, Separable Markov Random Field Model and Its Applications in Low Level Vision, In Press in IEEE Transactions on Image Processing [PDF]

Nathaniel R. Twarog, Marshall F. Tappen, Edward H. Adelson, Playing with Puffball: Simple Scale-Invariant Inflation for Use in Vision and Graphics Appeared in ACM Symposium on Applied Perception [PDF]

2011

H. Boyraz, M. F. Tappen, and R. Sukthankar, Localizing Actions through Sequential 2D Video Projections In CVPR4HB 2011 : Fourth IEEE Workshop on CVPR for Human Communicative Behavior Analysis [PDF]

M. F. Tappen, Recovering Shape from a Single Image of a Mirrored Surface from Curvature Constraints Appeared in the 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2011), pages 2545 - 2552 [PDF]

J. Sun and M. F. Tappen, Learning Non-Local Range Markov Random Field for Image Restoration Appeared in the 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2011), pages 2745-2752 [PDF]

S. Masood, C. Ellis, M. F. Tappen, J. J. LaViola, and R. Sukthankar, Measuring and Reducing Observational Latency when Recognizing Actions. To appear in the 6th IEEE Workshop on Human Computer Interaction: Real-Time Vision Aspects of Natural User Interfaces (ICCV 2011 Workshop)[PDF]

S. Masood, M. Khan, A. Nagaraja, and M. .F Tappen, Correcting Cuboid Corruption For Action Recognition In Complex Environment. To Appear in the 3rd IEEE Workshop on Video Event Categorization, Tagging and Retrieval for Real-World Applications (ICCV 2011 Workshop)[PDF]

2010

K. Tang, M. F. Tappen, R. Sukthankar, and C. Lampert, Optimizing One-Shot Recognition with Micro-Set Learning. Appeared in the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2010), pages 3027-3034 [PDF]

J. Zhu, K. G. G. Samuel, S. Masood, and M. F. Tappen, Learning to Recognize Shadows in Monochromatic Natural Images. Appeared in the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2010), pages 223-230, [PDF]

J. Sun and M. F. Tappen, Context-Constrained Hallucination for Image Super-Resolution. Appeared in the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2010), pages 231-238, [PDF]

2009

P. Scovanner and M.F. Tappen, Learning Pedestrian Dynamics from the Real World, Appeared in the 2009 International Conference on Computer Vision (ICCV) [PDF]

K. G. G. Samuel and M.F. Tappen, Learning Optimized MAP Estimates in Continuously-Valued MRF Models. Appeared in The Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) [PDF]

S. Masood, J. Zhu, and M. F. Tappen, Automatic Correction of Saturated Regions in Photographs using Cross-Channel Correlation Appeared in Pacific Graphics 2009 [PDF]

N. Khan, L. Tran, and M.F. Tappen, Training Many-Parameter Shape-from-Shading Models Using a Surface Database, Appeared in the International Conference on 3-D Digital Imaging and Modeling at ICCV 2009 [PDF]

2008

M.F. Tappen, K. G.G. Samuel, C.V. Dean, and D. Lyle, The Logistic Random Field -- A Convenient Graphical Model for Learning Parameters for MRF-based Labeling. Appeared in the Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) Accepted for Oral Presentation [PDF] - Correction on complexity of gradient computation [TXT].

R. S. Szeliski, R. Zabih, D. Scharstein, O. Veksler, V. Kolmogorov, A. Agarwala, M. Tappen, and C. Rother. A Comparative Study of Energy Minimization Methods for Markov Random Fields In IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 30, Number 6, June 2008 pp 1068-1080 [Project Page]

Brendan Moore, Marshall Tappen, and Hassan Foroosh. Learning Face Appearance under Different Lighting Conditions In The Second IEEE International Conference on Biometrics: Theory, Applications, and Systems. [PDF]

2007

M. F. Tappen. “Utilizing Variational Optimization to Learn Markov Random Fields”. Appeared in The Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) [PDF] -- A sample training implementation is also available [.ZIP]

M. F. Tappen, C. Liu, E. H. Adelson, and W. T. Freeman. “Learning Gaussian Conditional Random Fields for Low-Level Vision”. Appeared in The Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) [PDF] -- A sample training implementation is also available [.ZIP] - Correction on complexity of gradient computation [TXT].

2006 and Earlier

"Learning Continuous Models for Estimating Intrinsic Component Images", Doctoral Thesis, Massachusetts Institute of Technology, May 2006 [PDF]

M. F. Tappen, E. H. Adelson, and W. T. Freeman. “Estimating Intrinsic Component Images using Non-Linear Regression”. Appeared in The Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Volume 2, Pages 1992-1999, 2006 ,[PDF] The training and test data from this paper is also available as a .MAT file [.ZIP (10 MB)]

A Comparative Study of Energy Minimization Methods for Markov Random Fields. Rick Szeliski, Ramin Zabih, Daniel Scharstein, Olga Veksler, Vladimir Kolmogorov, Aseem Agarwala, Marshall Tappen, Carsten Rother. In Seventh European Conference on Computer Vision (ECCV 2002), volume 2, pages 16-29, Graz, May 2006. Springer-Verlag.

M. F. Tappen, W. T. Freeman, and E. H. Adelson. “Recovering Intrinsic Images from a Single Image”. In IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 27, Issue 9, September 2005, Pages 1459 - 1472[PDF]

M.F. Tappen, B. C. Russell, and W. T. Freeman. “Efficient Graphical Models for Processing Images”. The Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2004 [PDF]

M. F. Tappen and W. T. Freeman. “Comparison of Graph Cuts with Belief Propagation for Stereo, using Identical MRF Parameters”. In Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV), Pages 900 - 907, 2003 [PDF]

M. F. Tappen, B. C. Russell, and W. T. Freeman. “Exploiting the Sparse Derivative Prior for Super-Resolution and Image Demosaicing”. In Third International Workshop on Statistical and Computational Theories of Vision at ICCV 2003, 2003 [PDF]

M. F. Tappen, W. T. Freeman, and E. H. Adelson. “Recovering Intrinsic Images from a Single Image”. In S. T. S. Becker and K. Obermayer, editors, Advances in Neural Information Processing Systems 15, pages 1343-1350. MIT Press, Cambridge, MA, 2003.[PDF]

Teaching

  • Spring 2011, Fall 2011 - COP 3223 C Programming - Course Syllabus/Homepage
  • Fall 2008, 2009, 2010 - CAP 5415 - Computer Vision - Course Homepage (Also taught in 2006 and 2007)
  • Spring 2007 - CAP 6412 - Advanced Computer Vision - Course Homepage
  • Spring 2008, Fall 2008, Spring 2009, Spring 2010, Fall 2010 - EEL 5542 - Random Processes

Funding

  • RI: Large: Collaborative Research: Reconstructive Recognition - Uniting statistical scene understanding and physics-based visual. Role: PI at UCF. Funded by the National Science Foundation for 2012 - 2017

  • ARRA HCC: Medium: Collaborative Research: Computer Vision and Online Communities: A Symbiosis. Role: co-PI, in collaboration with Todd Zickler (Harvard) and Trevor Darrell (Berkeley). Funded by the National Science Foundation for 2009-2013

  • REU Site: Research Experience for Undergraduates in Computer Vision, Role: Senior Personnel (PI: M. Shah) - Funded by National Science Foundation for 2009-2012

  • Automatic Target Recognition for Personnel Imaging Systems, Role: PI, Funded for 2009-2010 by the Department of Homeland Security under a sub-contract from Applied Research Associates.

  • RI: Small: Learning-Based Systems for Single-Image Photometric Reconstruction, Role: PI - Funded by the National Science Foundation for 2009-2012

  • Data and Algorithms for Estimating Scene Causes from Real-World Images, Role: PI, Funded by the National Geo-Spatial Intelligence Agency - 2008

  • RAOS: TO#16 - Technical Consulting in Support of High Performance Computing Applications in Adversarial Reasoning, Role:PI - Funded by RDECOM for 2008-2009

Personal

The Tappen 
Family
The latest Tappen family picture. I am fortunate to be married to the incomparable Joy Chan Tappen M.D. -- I married way up.
On the beach at Sanibel Island
Trying to keep my little mermaid from returning to the ocean.