About Group

I lead the UT-Austin Image and Video Computing (IVC) Group. Our aim is to create computing systems that enable and accelerate the analysis of visual information, as a critical precursor to discoveries and innovations that can benefit society at large. Our research involves computer vision, machine learning, crowdsourcing, human computation, human-computer interaction, accessibility, and (bio)medical image analysis. We develop both scalable automated algorithms and crowdsourced human intelligence systems for analyzing images and videos. Research problems addressed by our group include salient object detection, object segmentation, object tracking, (bio)medical image and video analysis, visual question answering, assistive technologies for people who are blind and with low vision, and image inpainting. Our work is currently supported by funding from the National Science Foundation, Silicon Valley Community Foundation, Microsoft, Adobe, and Amazon.

Our group is also a part of the UT Austin Intelligent Systems Group.

Members



Abigale Stangl
Postdoctoral Fellow


Yinan Zhao
PhD Student


Samreen Anjum
PhD Student


Tai-Yin Chiu
PhD Student


Chongyan Chen
PhD Student


Sanjana Tripathi
Masters Student

Alumni

Meng Zhang, MSIS at University of Texas at Austin.
Xiaoyu (Edith) Zeng, MSIS at University of Texas at Austin. Now at Apple.
Yanan Wang, MSIS at University of Texas at Austin. Now PhD student at University of Wisconsin-Madison.
Chi (Benny) Lin, MSIS at University of Texas at Austin, 2019. Now at Houzz.
Dr. Mehrnoosh Sameki, PhD at Boston University (co-advised with Margrit Betke), 2017. Now at Microsoft, previously at Rue La La.

Visitors

Qing Li, Visiting Research Fellow, 2018. Now PhD student at UCLA.

Prospective Students

My goal for individuals joining this group is to guide them to identify their dream jobs; arm them with the knowledge, skills, and community to make their dreams become a reality; and support them to make a positive social impact along the way. If you are interested in joining, please review this FAQ page first.