 |
Jonathan C. Stroud
Beyster 3944
|
About
I am a Ph.D. student in Computer Science and Engineering at the University of Michigan, where I work with Jia Deng. My primary research interests are in deep learning for human action recognition and video classification.
I am the co-founder of The Michigan Data Science Team, a student group on campus that solves interesting data science challenges.
I received my Bachelors degree from the University of California, Irvine, where I worked with Alexander Ihler.
News
8/20 I have graduated! I will be joining Waymo next month.
6/20 Our team co-won the Kinetics Challenge at CVPR 2020.
12/19 Our paper “D3D: Distilled 3D Networks for Video Action Recognition” was accepted to WACV 2020.
5/19 I was a summer intern (again!) at Google Research in Mountain View, CA.
5/18 I was a summer intern at Google Research in Mountain View, CA.
7/17 Our team placed second in the Charades Challenge at CVPR 2017.
2/17 Our paper “Temporal Action Localization by Structured Maximal Sums” was accepted to CVPR 2017.
Publications
Compositional Temporal Visual Grounding of Natural Language Event Descriptions.Jonathan C. Stroud, Ryan McCaffrey, Rada Mihalcea, Jia Deng, and Olga Russakovsky.
[paper] [project page]
D3D: Distilled 3D Networks for Video Action Recognition.
Jonathan C. Stroud, David A. Ross, Chen Sun, Jia Deng, and Rahul Sukthankar.
Winter Conference on Applications of Computer Vision (WACV), 2020.
[paper] [project page]
Temporal Action Localization by Structured Maximal Sums.
Zehuan Yuan, Jonathan C. Stroud, Tong Lu, and Jia Deng.
Computer Vision and Pattern Recognition (CVPR), 2017.
[paper] [code]