Everley Tseng is a Ph.D. candidate in Computer Science at the University of Colorado Boulder, advised by Professor Danna Gurari in the Image and Video Computing (IVC) Group. Her research advances computer vision through dataset-driven discovery of new problem spaces. She develops benchmarks and evaluation frameworks that expose the limitations of current vision-language models in real-world applications, especially for people who are blind or have low vision. Her work spans vision-language modeling, dataset curation, visual privacy, image segmentation, and few-shot learning, resulting in publicly released datasets such as VizWiz-FewShot and BIV-Priv-Seg. Everley is passionate about bridging academic innovation and industry-scale deployment, focusing on creating trustworthy and efficient visual AI systems that address real accessibility and privacy challenges.
LinkedIn • Google Scholar • GitHub • Email
EDUCATION
PhD, Computer Science, University of Colorado Boulder (2021-Present)
MS, Computational Intelligence, College of AI, National Chiao Tung University (2019-2021)
BS, Engineering and System Science, National Tsing Hua University (2013-2017)
WORK EXPERIENCES
AI/ML Intern, Marvell Semiconductor, Inc. (2025-2025)
Computer Vision Engineer, Coretronic Corporation (2017-2019)
Research Intern, Lite-On Technology Corporation (2017-2017)
PUBLICATIONS
Visual Privacy Management with Generative AI for Blind and Low-Vision People, Tanusree Sharma, Yu-Yun Tseng, Lotus Zhang, Ayae Ide, Kelly Avery Mack, Leah Findlater, Danna Gurari, Yang Wang. The 26th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS), 2025. [paper]
Acknowledging Focus Ambiguity in Visual Questions, Chongyan Chen, Yu-Yun Tseng, Zhuoheng Li, Anush Venkatesh, Danna Gurari. International Conference on Computer Vision (ICCV), 2025. [paper]
BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments, Yu-Yun Tseng, Tanusree Sharma, Lotus Zhang, Abigale Stangl, Leah Findlater, Yang Wang, Danna Gurari. Oral presentation (top 8%), IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025. [paper, oral presentation]
Learning-Based WiFi Fingerprint Inpainting via Generative Adversarial Networks, Yu Chan, Pin-Yu Lin, Yu-Yun Tseng, Jen-Jee Chen, Yu-Chee Tseng. IEEE International Conference on Computer Communications and Networks (ICCCN), 2024. [paper]
Designing Accessible Obfuscation Support for Blind Individuals’ Visual Privacy Management, Lotus Zhang, Tanusree Sharma, Abigale Stangl, Yu-Yun Tseng, Inan Xu, Danna Gurari, Yang Wang, Leah Findlater. ACM Conference on Human Factors in Computing Systems (CHI), 2024. [paper]
Disability-First Design and Creation of A Dataset with Private Visual Information, Tanusree Sharma, Abigale Stangl, Lotus Zhang, Yu-Yun Tseng, Inan Xu, Leah Findlater, Danna Gurari, Yang Wang. ACM Conference on Human Factors in Computing Systems (CHI), 2023. [paper]
VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments, Yu-Yun Tseng, Alexander Bell, Danna Gurari. European Conference on Computer Vision (ECCV), 2022. [paper]
Efficient Vehicle Counting Based on Time-Spatial Images by Neural Networks, Yu-Yun Tseng, Tzu-Chien Hsu, Jen-Jee Chen, Yu-Chee Tseng. IEEE International Conference on Mobile Ad-Hoc and Smart Systems (MASS), 2021. [paper]
Computer Vision-Assisted Instant Alerts in 5G, Yu-Yun Tseng, Po-Min Hsu, Jen-Jee Chen, Yu-Chee Tseng. IEEE International Conference on Computer Communications and Networks (ICCCN), 2020. [paper]