What's new





Dancing with Turks

I-K Chiang, I. Spiro, S. Lee, A. Lees, J. Liu, C. Bregler and Y. Liu

ACM MULTIMEDIA 2015, Long Paper (acceptance rate: 22%)

Project Page



Representation of Maximally Regular Textures in Human Visual Cortex

Kohler, Clarke, Yakovleva, Liu, Norcia

Journal of Neuroscience

In Press (Dec. 2015)

Project Page


Parametric Responses to Rotation Symmetry in Mid-level Visual Cortex

Kohler, Yakovleva, Clarke, Liu, Norcia

Project Page


The salience of Lower-Order Features in Highly Self-Similar Walllpaper Groups

Vedak, Gilmore, Kohler, Norcia, Liu

Vision Science Society

Project Page





CSE 597E Deep-learning for Pattern Discovery

Wednesday 2-4:30pm, EES 120

In this course, we will learn to use computational tools related to deep learning and mathematical theory on pattern representation. Students will be trained to have a hands-on experience of applying theory and algorithms to discover regularity/patterns from real, multidimensional, noisy data sets.


Computer Graphics



Highlights Movie




Pattern Recognition and Machine Learning CSE 583/EE 552 (Graduate Level)


Theoretical, Computational and Experimental Regularity on Interdisciplinary, Large Data Sets

CSE 597K

Schedule # = 537469

Where: IST 210

When: Wednesdays 2:30-5pm (once per week)

Instructor: Professor Yanxi Liu

This is a course on computational methods for digital data that is across scale, modality and application domains. Our methodology is a unique mixture of theoretical and experimental bases drawn from group theory, pattern theory, statistical learning theory as well as human/animal/insect visual perception research. We aim at automatic pattern discovery, comparison and learning. The students are trained throughout the course to apply theory and algorithms to real world scientific data, with an emphasis on discovering hidden patterns automatically from large data sets, including imagery/video of human faces, urban scenes, zebra in the wild, crowds/cell videos, volumetric images of Zebrafish, C. elegans, neuroradiology images (MR, CT, EEG) and MoCap data of human dance/movements. Your own research data sets are welcome.

A similar course was taught by Professor Liu at Stanford University last winter: http://graphics.stanford.edu/courses/cs468-14-winter/

Another similar course taught by Professor Liu at PSU in 2011:





IEEE TPAMI Associate Editor


CVIU Editorial Board




NIH P41 Site Visit