I am a Professor in the Department of Computer Science at the University of Texas at Austin, where I lead the UT-Austin Computer Vision Group. I was elected to the Academy of Distinguished Teachers at UT Austin in 2017. I received my Ph.D. from MIT in the Computer Science and Artificial Intelligence Laboratory in 2006.
ML@UT: UT Austin has broad and deep expertise in machine learning and artificial intelligence, spanned by groups across several departments on campus. UT Austin is also home of an NSF AI Institute focused on machine learning.
Ego(-Exo)4D
Ego4D provides egocentric video capture of daily life activity around the world as well as a suite of benchmarks establishing fundamental tasks in egocentric perception that are the focus of annual competitions. See overview here, and our CVPR 2022 paper. Data is here. Check out the annual benchmark challenges for both.
My primary interests are video, multimodal perception, embodied AI (vision for robotics, perception for action), and
visual recognition.Recent and ongoing projects in the group consider first-person "egocentric" computer vision, navigation and exploration in 3D spaces, audio-visual learning from video, activity recognition, affordance models from video, vision for fashion (forecasting, styles, trends, recommendation, attributes), and video summarization.
Publications page with links to code, slides, and project pages. Or, sorted [by year] [by topic].
Code
download
page (see per paper project pages for latest)
Datasets
download page
Student
theses
Romy Luo
Arjun Somayazulu
Joungbin An
Danny Tran
Wu Chi Hsuan (Jason)
Ali Salamatian
Devi Parikh Visiting Research Fellow, 2010-2011. Now Associate Professor at Georgia Tech
Lu Zheng Postdoctoral Research Fellow, 2012-2013. Now Assistant Professor at City University of Hong Kong
Boqing Gong, Visiting PhD student from Prof. Fei Sha's lab at USC, 2012. Assistant Professor at University of Central Florida. Now at Google Research
Hao Jiang, Visiting Professor from Boston College, 2015-2016.
Antonino Furnari, Visiting PhD student from Prof. Giovanni Maria Farinella's lab at Univ. of Catania, 2016.
Ziad Al-Halah, Visiting PhD student from Prof. Stiefelhagen's lab at Karlsruhe Institute of Technology, 2016.
Danna Gurari, Postdoctoral Research Fellow, 2015-2017. Now Assistant Professor at University of Colorado Boulder
Yong Jae Lee Ph.D. (2012). Postdoctoral Associate at UC-Berkeley. Assistant Professor at UC-Davis and now Associate Professor at UW-Madison.
Jeff Donahue, B.S., Turing Scholars Honors Thesis (2011). Ph.D. student at UC-Berkeley. Now at DeepMind.
Andy Luong, B.S., Turing Scholars Honors Thesis (2011), Best Undergraduate Thesis Award. Now at Microsoft.
Lucy Liang, B.S., Turing Scholars Honors Thesis (2012), Best Undergraduate Thesis Award. Now at Microsoft.
Nona Sirakova, B.S., Turing Scholars Honors Thesis (2013). Now at University of Washington.
Tomas McCandless, B.S. Turing Scholars Honors Thesis (2013).
Sunil Bandla, M.S. (2013). Now at Microsoft.
Jaechul Kim Ph.D. (2013). Now at Amazon Research.
Sung Ju Hwang Ph.D. (2013). Now Assistant Professor at KAIST.
Adriana Kovashka, Ph.D. (2014). Now Assistant Professor at University of Pittsburgh.
Chao-Yeh Chen, Ph.D. (2016). Now at Google.
Suyog Jain, Ph.D. (2017). Now at PathAI.
Josh Kelle, M.S. (2017). Now at Pinterest.
Steven Chen, B.S., Turing Scholars Honors Thesis (2017). Now a Masters student at Stanford University.
Evonne Ng, B.S., Turing Scholars Honors Thesis (2019). Now a PhD student at UC Berkeley.
Saket Sadani, B.S., Turing Scholars Honors Thesis (2019).
Andrew Li, B.S., Turing Scholars Honors Thesis (2019). Now at Google.
Dinesh Jayaraman, Ph.D. (2017). Samsung Ph.D. Fellowship Postdoc at UC-Berkeley. Now Assistant Professor at UPenn.
Aron Yu Ph.D. (2019). Now at Home Depot AI.
Bo Xiong Ph.D. (2019). Now at Facebook AI Research.
Yu-Chuan Su,Ph.D. (2019). Google PhD Fellowship in 2017. Now at Google Research.
Ruohan Gao Ph.D. (2021). Now a postdoc at Stanford --> Assistant Professor at UMD.
Kimberly (Wei-Lin) Hsiao Ph.D. (2021) Now at Amazon.
Rishabh Garg, MS (2021) Now at Amazon.
Tushar Nagarajan, Ph.D (2022) Now at Meta FAIR
Santhosh Ramakrishnan, Ph.D. (2023) Now at Apple
Changan Chen, Ph.D. (2024) Now at Stanford University, co-founder of Rhoda AI
Ami Baid, B.S. Turing Scholars Honors Thesis (2026). Now at Stanford.
Sagnik Majumder , Ph.D. (2026). Now at Google.
Ashutosh Kumar, Ph.D. (2026), Now at Meta.
Sherry Xue, Ph.D. (2026), Now at Google DeepMind
Program Chair: CVPR 2015
Program Chair: NIPS 2018
Program Chair: ICCV 2023
Editorial Board: IJCV
Area Chair: CVPR 2009, ICCV 2009, ICCV 2011, ECCV 2012, ACCV 2012, NIPS 2012, CVPR 2013, ICCV 2013, ECCV 2014, ICML 2015, ICML 2016, ECCV 2016, ICCV 2017, ECCV 2018, CVPR 2019, CVPR 2020
Senior Area Chair: NIPS 2017, ICML 2019, NeurIPS 2020, CVPR 2025, CVPR 2026
Program Committee / Reviewer: CVPR 2006, 2007, 2010, 2011, 2012, 2016; ICCV 2007, 2015; ECCV 2008, 2010; NIPS 2005, 2007, 2008, 2009, 2010, 2015, AAAI 2011, 2014, SIGGRAPH 2014, 2017
CS 381V: Visual Recognition (Fall 2025) -- Breadth course for CS PhD students
CS 381V: Visual Recognition (Spring 2025) -- Breadth course for CS PhD students
CS 376: Computer Vision (Spring 2018)
CS 381V: Visual Recognition (Fall 2017) -- a Diversity course for CS PhD students
CS 378H: Honors Machine Learning and Vision (Spring 2017)
CS 381V: Visual Recognition (Fall 2016) -- a Diversity course for CS PhD students
CS 381V: Visual Recognition (Spring 2016) -- a Diversity course for CS PhD students
CS 378H: Honors Machine Learning and Vision (Fall 2015)
CS 343H: Honors Artificial Intelligence (Spring 2014)
Short Course / Tutorial on Attributes at CVPR 2013
CS395T Visual Recognition (Fall 2012) -- a Diversity course for CS PhD students
CS 395T Visual Recognition (Fall 2011) -- a Diversity course for CS PhD students
CS 376: Computer Vision (Spring 2011)
CS 395T: (Special Topics in) Computer Vision : Object Recognition (Spring 2010)
CS 378: Computer Vision (Fall 2009)
CS 395T: Visual Recognition and Search (Spring 2009)
CS 378: Computer Vision (Fall 2008)
AAAI 2008 Tutorial on Visual Recognition, co-taught with Bastian Leibe (July 2008)
CS 395T: Visual Recognition and Search (Spring 2008)
CS 378 / 395T: Computer Vision (Fall 2007)
CS 395T: Object Recognition (Spring 2007)
Introduction to Computer Science, for the Women�s Technology Program (MIT, Summer 2005)
| Email: |
grauman,
at sign, cs dot utexas dot edu (best way to contact
me) |
| Campus
office: |
GDC 4.726
(south building) |
| Mailing
address: |
Department
of Computer Science University of Texas at Austin 2317 Speedway D9500 Austin, TX 78712-1757 |
| Campus
mail: |
Mail
code
D9500 |
- NeurIPS 2020 HAMLETS workshop (Dec 2020) and Stanford Vision Lab (Sept 2020)
- "People Watching for Agent Learning" [ppt]
- NeurIPS 2020
Self-Supervised Learning - Theory and Practice
workshop, Dec 2020
- "Self-supervised Learning with
Sight, Sound, and Space" [ppt]
- Google Research, Sept 2020
- "Sights, Sounds, and Space: Audio-Visual Learning in 3D Environments" [ppt]
- Long-Term Visual Localization, Visual Odometry and Geometric and Learning-based SLAM Workshop, CVPR 2020, June 2020
- ACM International Web Search and Data Mining Conference (WSDM), Feb 2020
- "Computer Vision for Fashion: From Individual Recommendations to World-wide Trends" [ppt]
- International Conference on Intelligent Robotics and Systems (IROS), Nov 2019
- "Embodied Visual Learning"
[ppt]
- Speech and Audio in the Northeast, Columbia University, Oct 2019
- "Eyes and Ears: Learning to Disentangle Object Sounds in Unlabeled Video" [ppt]
- University of Minnesota Cray Colloquium and University of Utah AI Lecture Series, Jan 2020
- "First-Person Perception and Interaction" [ppt]
- Self-supervised Learning in Audio and Speech Workshop, ICML 2020, July 2020
- Retail Vision Workshop, CVPR 2020, June 2020
- 3rd
Workshop on Computer Vision For Fashion, Art and
Design, CVPR 2020, June 2020
- Sight and Sound Workshop, CVPR 2020, June 2020
- Omnidirectional Computer Vision Workshop, CVPR 2020, June 2020
- EPIC
- Sixth International Workshop on Egocentric
Perception, Interaction and Computing, CVPR
2020, June 2020
- 3D Scene
Understanding for Vision, Graphics, and Robotics
Workshop, CVPR 2020, June 2020
- Midwest Machine Learning Symposium keynote, June 2019
- "First-Person Perception by
Anticipating the Unseen and Unheard" [ppt]
- Multimodal Learning from Videos, CVPR workshop, June 2019
- "Learning from First-Person
Video" [ppt]
- 360 Indoor Scene Understanding and Modeling (SUMO), CVPR workshop, June 2019
- "Where to Look: Navigating and
Compressing 360 Video" [ppt]
- Target Re-Identification and Multi-Target Multi-Camera Tracking, CVPR workshop, June 2019
- "Less is More: Learning to Find
Video Highlights" [ppt]
- 3D Scene Generation, CVPR workshop, June 2019
- Learning to Explore 3D
Scenes" [ppt]
- Learning from Unlabeled Videos, CVPR workshop, June 2019
- "Multimodal Learning from
Unlabeled Video" [ppt]
- Multimodal Learning and Applications, CVPR workshop, June 2019
- "Disentangling Object Sounds in
Video" [ppt]
- Visual Understanding by Learning from Web Data, CVPR workshop, June 2019
- "Learning about Fashion from Web Photos" [ppt]
- Computer Vision Applications for Mixed Reality Headsets, CVPR workshop, June 2019
- "Human-object Interaction in
First-Person Video" [ppt]
- Cornell Tech, Learning Machines Seminar, New York City, March 2019
- MIT-IBM AI seminar, Cambridge, August 2018
- NVIDIA Research, Santa Clara, June 2018
- "Learning Where to Look and
Listen: Egocentric and 360 Computer Vision" [pdf]
- CVPR Workshop on Understanding Subjective Attributes of Data, Salt Lake City, June 2018
- "Visual Styles in Fashion Photos" [pdf]
- CVPR Workshop on Language and Vision, Salt Lake City, June 2018
- CVPR
Workshop on Deep Learning and Robotic Vision,
Salt Lake City, June 2018
- "Towards Embodied Visual
Learning" [pdf]
- ICLR, International Conference on Learning Representations, Keynote, May 2018
- "Visual Learning with Unlabeled
Video and Look-Around Policies" [pdf]
- AAAI,
31st Conference on Artificial Intelligence
Keynote, Feb 2017
- "Learning How to Move and Where
to Look from Unlabeled Video" [pdf]
- GroupSight workshop on Human Computation for Image and Video Analysis, HCOMP, Nov 2016.
- "Active and Interactive Image and
Video Segmentation" [pdf]
- SUNw: Scene Understanding Workshop, CVPR, June 2016
- "Action and Interaction for Scene Understanding" [pdf]
- Moving Cameras Meet Video Surveillance: From Body-Borne Cameras to Drones, CVPR, June 2016
- "Summarizing Long First-Person Videos" [pdf]