Designing Computer Vision Solutions for Real-World Applications

Abstract: While computer vision (CV) systems are transforming our daily lives, they still struggle to meet many real-world needs.  In this talk, I will present three ways our team is addressing misalignments between current CV paradigms and what is needed for real-world applications.  This will include: (1) creating large-scale datasets that fill gaps in representing authentic cases; (2) designing efficient hybrid algorithm-crowd partnerships to compensate for algorithm shortcomings; and (3) introducing compact models that can perform tasks accurately with less computational expense.

Bio: Danna Gurari is an Assistant Professor as well as Director of the Image and Video Computing group in the Computer Science Department at University of Colorado Boulder. Her research interests span computer vision, machine learning, human computation, crowdsourcing, human computer partnerships, accessibility, and (bio)medical image analysis. Her group focuses on creating computing systems that enable and accelerate the analysis of visual information. She and her work has been recognized with research awards from WACV, CHI, CSCW, ASIS&T, HCOMP GroupSight, MICCAI IMIC, and AAPM. Gurari's research has been supported by the National Science Foundation, Silicon Valley Community Foundation's Chan Zuckerberg Initiative, Microsoft, Adobe, Amazon, Wings of Hope, and Coleman Institute. 

Please join us in ECCR 265 or on Zoom: https://cuboulder.zoom.us/j/91008309605