Chen-Ping Yu 

     Co-Founder, CEO at Phiar
     Previously Postdoctoral Fellow at Harvard

     Mail to:
     200 Portland St, Fl 5
     Boston, MA 02114

     E-mail: chenping.yu at phiar dot net

     Phone: (585) 576 - 5839

About Me (as of June 2017)

I am a postdoctoral research fellow supervised by Prof. Talia Konkle at the Cognitive and Neural Organization Lab (Konklab), that is part of Harvard Vision Sciences Lab in the psychology department at Harvard University. I obtained my Ph.D in the computer science department at Stony Brook University, co-advised by Prof. Dimitris Samaras and Prof. Greg Zelinsky. Before Stony Brook, I had an M.S. in computer science and engineering from the Pennsylvania State University in the Laboratory for Perception, Action, and Cognition (LPAC), working on computer vision and medical image analysis advised by Prof. Yanxi Liu. I also had an earlier M.S. in computer science from Rochester Institute of Technology (RIT) where I have done work in modelling visual cortex receptive fields, and was co-advised by Prof. Roger Gaborski of the Lab for Computational Studies at RIT, and Prof. Charles Duffy of the Cognitive Neuroscience Lab at University of Rochester Medical Center (URMC)

My research interest includes computer vision, biological vision models, and machine learning. I am currently working on building biologically-informed deep learning models for predicting behavioral and neuronal data, exploring and investigating the transformation of object information within a deep CNN, and studying new shape descriptors at the Cognitive and Neural Organization Lab (Konklab).



11/08/2017 - Paper accepted at NIPS 2017: Squared Earth Mover's Distance Loss for Training Deep Neural Networks on Ordered-Classes.

10/01/2017 - Paper accepted at ICCV 2017: Co-Localization with Category-Consistent Features and Geodesic Distance Co-Propagation.

11/17/2016 - New paper posted on arXiv: Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks.

08/15/2016 - Paper accepted at ACCV 2016: Geodesic distance histogram feature for video segmentation.

07/19/2016 - Paper accepted at ECCV 2016: Large-scale training of shadow detectors with noisily-annotated shadow examples.

05/16/2016 - GSEU Professional Development Grant was awarded!

02/15/2016 - One oral and two poster presentations were accepted at the VSS 2016!

02/12/2016 - Presentation at Harvard Vision Sciences Lab: Category-consistent features (CCFs) for visual category representation.

02/04/2016 - Our paper, Searching for category-consistent features: A computational approach to understanding visual category representation, was accepted at Psychological Science!

10/15/2015 - Travel award for the Doctoral Consortium at ICCV 2015.

09/01/2015 - Our paper Efficient video segmentation using parametric graph partitioning was accepted at ICCV 2015!

07/10/2015 - Invited tech talk at JPMorgan Chase: Parametric graph partitioning and its applications.

10/21/2014 - Talk at Stony Brook Cognitive Science Colloquium: Modeling visual clutter perception using proto-objects.

02/05/2014 - Invited talk at Shutterstock: Visual search and image clutter.