Stella Yu
Director, ICSI Vision Group
Senior Fellow, Berkeley Institute for Data Science
Faculty, Computer Science and Vision Science
University of California, Berkeley
Contact: stellayu @ berkeley . edu


Teaching
CS280 Computer Vision Spring 2017
CS189 / 289A Machine Learning Fall 2017


Publications

As a vision scientist, I subscribe to the view that visual perception presents not just a fascinating computational problem, but more importantly an intelligent solution for large-scale data mining and pattern recognition applications. I study visual perception from multiple perspectives: human vision, computer vision, robotic vision, and artistic vision.

I am particularly interested in human vision's ingenuity and immediacy at resolving a property or region of interest from its context. The context is not a mere conglomeration of pieces, but an organized whole of interrelated elements. Only in such an organization can an object be assigned a place and be singled out from the context without relinquishing the effects of the context.

My approach to computer vision is thus about establishing parts in relation, organizing them into a whole, and singling out the aspect of interest from the whole. In modeling visual organization, I have developed new tools in spectral graph theory and machine learning to effectively uncover the relational structure of large-scale data. I have also pursued efficient representation and computation by learning from artists and exploring the connections between Art and Vision.



Members
Zhongqi Miao, Jyh-Jing Hwang, Tsung-Wei Ke, Baladitya Yellapragada, Patrick Virtue
Dr. Zhirong Wu, Dr. Ziwei Liu, Dr. Sascha Hornauer, Dr. Matthias Demant
Jiayun Wang, Riley Edmunds, Tapabrata Chakraborty, Sebastian Palacio
Dr. Seyed Ali Amirshahi, Asha Anoosheh, Weiyu Zhang, Dr. Dimitri Lisin, Dr. Christina Pavlopoulou, Dr. Elena Bernardis