Department of Computer Science and Engineering
University of South Carolina
Columbia, SC 29208, USA
Hongkai Yu is currently a Ph.D. Candidate in the Computer Vision Lab at University of South Carolina under the supervision of Dr. Song Wang. He earned his M.S. in Traffic Information Engineering and Control and B.S. in Automation from Chang'an University, Xi'an, China in 2012 and 2009 respectively. In 2017 summer, I worked at TuSimple, San Diego, CA as a Research & Develop intern for autonomous driving.
Visual Data Processing: Computer Vision, Image Processing
Machine Learning, Deep Learning
Traffic Data Understanding: Autonomous Driving, Intelligent Transportation Systems
07/2017: one paper has been accepted by ICCV 2017.
05/2017: two papers have been accepted to ICIP 2017.
* indicates co-first authors.
4. Jun Zhou, Haozhou Yu, Karen Smith, Colin Wilder, Hongkai Yu, Song Wang. Identifying Designs from Incomplete, Fragmented Cultural Heritage Objects by Curve-Pattern Matching, Journal of Electronic Imaging, 2017.
3. Youjie Zhou*, Hongkai Yu*, Jeff Simmons, Craig Przybyla and Song Wang. Large-Scale Fiber Tracking through Sparsely Sampled Image Sequences of Composite Materials. IEEE Transactions on Image Processing, 2016.
2. Dazhou Guo, Julius Fridriksson, Paul Fillmore, Christopher Rorden, Hongkai Yu, Kang Zheng and Song Wang. Automated Lesion Detection on MRI Scans using Combined Unsupervised and Supervised Methods. BMC Medical Imaging, 2015.
[PDF | Code]
1. Shuguang Li, Hongkai Yu, Jingru Zhang, Kaixin Yang and Bin Ran. Video-based Traffic Data Collection System for Multiple Vehicle Types. Journal of IET Intelligent Transport Systems, 2014. PDF
11. Kang Zheng, Xiaochuan Fan, Yuewei Lin, Hao Guo, Hongkai Yu, Dazhou Guo, and Song Wang. Learning
View-invariant Features for Person Identification in Temporally Synchronized Videos Taken by Wearable Cameras. IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017.
10. Hongkai Yu, Youjie Zhou, Hui Qian, Min Xian and Song Wang. LooseCut: Interactive Image Segmentation with Loosely Bounded Boxes. IEEE International Conference on Image Processing (ICIP), Beijing, China, 2017. Code is available upon request
9. Youjie Zhou, Hongkai Yu and Song Wang. Feature Sampling Strategies for Action Recognition. IEEE International Conference on Image Processing (ICIP), Beijing, China, 2017. [PDF | Code]
8. Hongkai Yu, Jeff Simmons, Craig P. Przybyla, and Song Wang. On-the-fly Performance Evaluation of Large-scale Fiber Tracking. IS&T International Symposium on Electronic Imaging, Burlingame, CA, 2017. PDF
7. Kang Zheng, Hao Guo, Xiaochuan Fan, Hongkai Yu and Song Wang. Identifying Same Persons from Temporally Synchronized Videos Taken by Multiple Wearable Cameras. IEEE Conference on Computer Vision and Pattern Recognition Workshop on ChaLearn Looking at People (CVPRW), Las Vegas, Nev, 2016. PDF
6. Hongkai Yu*, Youjie Zhou*, Jeff Simmons, Craig Przybyla, Yuewei Lin, Xiaochuan Fan, Yang Mi and Song Wang.
Groupwise Tracking of Crowded Similar-Appearance Targets from Low-Continuity Image Sequences.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nev, 2016. (Spotlight oral)
5. Yuewei Lin, Kareem Abdelfatah, Youjie Zhou, Xiaochuan Fan, Hongkai Yu, Hui Qian and Song Wang.
Co-interest Person Detection from Multiple Wearable Camera Videos. IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015. PDF
4. Hongkai Yu, Min Xian and Xiaojun Qi. Unsupervised Cosegmentation Based on a New
Global GMM Constraint in MRF. IEEE International Conference on Image Processing
(ICIP), Paris, France, 2014. [PDF | Code]
3. Hongkai Yu and Xiaojun Qi. Unsupervised Cosegmentation Based on Superpixel Matching
and FastGrabCut. IEEE International Conference on Multimedia and Expo (ICME), Chengdu, China, 2014. PDF
2. Shuguang Li, Hongkai Yu, Jingru Zhang. Video-based Traffic Data Collection System for
Multiple Vehicle Types. Compendium of Papers CD-ROM for 91st TRB Annual Meeting, Washington, D.C., 2012.
1. Shuguang Li, Hongkai Yu, Jingru Zhang, Ke Yue. Multi-type Vehicles' Traffic Data
Collection Using Video Processing. The 2nd International Conference on Intelligent Control and Information Processing (ICICIP), Harbin, China, 2011.