Danna (pronounced similar to "Donna") Gurari; aka, Dr. G
Computer Science Department
University of Colorado Boulder
Office Location: ECES 134 (1111 Engineering Drive)
Email: danna dot gurari, at sign, colorado dot edu
(Current/Prospective Students: please read my FAQ before emailing me)
Danna Gurari is an Assistant Professor as well as Founding 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 interaction, accessibility, and (bio)medical image analysis. Her group focuses on creating computing systems that enable and accelerate the analysis of visual information. Her work has been recognized with the 2020 Best Paper Honorable Mention Award at CSCW, 2020 SIG-USE Innovation Award at ASIS&T, 2017 Best Paper Honorable Mention Award at CHI, Researcher Excellence Award from the Boston University Computer Science Department in 2015, 2014 Best Paper Award for Innovative Idea at MICCAI IMIC, and 2013 Best Paper Award at WACV. Gurari's research has been supported by the National Science Foundation, Silicon Valley Community Foundation's Chan Zuckerberg Initiative, Microsoft, Adobe, and Amazon. She received her Ph.D. from Boston University's Computer Science Department (advised by Dr. Margrit Betke), then served as a postdoctoral fellow in the Computer Science Department at University of Texas at Austin (supervised by Dr. Kristen Grauman), and then served as an Assistant Professor in the School of Information at University of Texas at Austin. Before that, she held industry positions at two leading technology companies: Boulder Imaging and Raytheon.
- August 2021: I am joining the Computer Science Department at University Colorado Boulder as an Assistant Professor.
- July 2021: I received a NSF SaTC grant with Co-PIs Leah Findlater and Yang Wang.
- January 2021: I am co-organizing two workshops that will be held in conjunction with CVPR 2021: VizWiz Grand Challenge and UG2+ Prize Challenge: Bridging the Gap Between Computational Photography and Visual Recognition.
- January 2021: A dataset challenge around our CTMC multi-object tracking dataset is now live: https://motchallenge.net/data/CTMC-v1/. Submissions will be accepted through May 21. Winners for the challenge will be announced at the CVMI workshop, that will be held in conjunction with CVPR 2021.
- January 2021: Two dataset challenges around our VizWiz dataset are now live: Visual Question Answering and Image Captioning. Submissions will be accepted through May 21. Winners for both challenges will be announced at our workshop, VizWiz Grand Challenge, that will be held in conjunction with CVPR 2021.
- January 2021: I will be presenting April 20 at the The Third Workshop Beyond Vision and Language: Integrating Real-world Knowledge which will be held in conjunction with European Chapter of the Association for Computational Linguistics.
- January 2021: I will be presenting at an IBM Research seminar on March 23.
- October 2020: I will be presenting at the Sight Tech Global conference on inclusive dataset creation on December 2-3.
- October 2020: I received a Microsoft AI4A grant to support the design of inclusive datasets for machine learning.
- October 2020: Our team was recognized with the CSCW Best Paper Honorable Mention Award for our paper "Vision Skills Needed to Answer Visual Questions".
- October 2020: Our team was recognized with the ASIS&T SIG-USE Innovation Award for our paper "Quality of Images Showing Medication Packaging from Individuals with Vision Impairments: Implications for the Design of Visual Question Answering Applications".
- April 2021: Allen Institute for AI NLP Highlights Podcast
- December 2020: Sight Tech Global Conference
- June 2020: Visual Question Answering and Dialog workshop
- July 2019: Microsoft Faculty Summit about "The Future of Work"
- Video of Talk
- Video of Panel Discussion
- Slides: "Learning to Describe Images Taken by People Who Are Blind"
- Accessible Version of Slides: "Learning to Describe Images Taken by People Who Are Blind"
- July 2019: Workshop on "Crowd, Cloud and the Future of Work" at the Microsoft Faculty Summit
- Video of Talk
- Slides: "Learning to Recognize When and Why a Crowd Will Offer Different Answers to a Visual Question"
- April 2019: Army's Mad Scientists: Ethics & the Future of AI Innovation Panel
- September 2018: Workshop on Shortcomings in Vision and Language (SiVL)
- Slides: "Visual Questions: Learning to Assist Blind People and Detect When/Why a Crowd Will Disagree on the Answer"
- September 2017: MICCAI Workshop on Large-scale Annotation of Biomedical data and Expert Label Synthesis (LABELS)