Yi Zhu


Email: yzhu25(at)ucmerced.edu

Office: SE2 Rm 213E, 5200 N Lake Rd, Merced, CA 95343

Biography

I am a final year PhD candidate at UC Merced, working with Shawn Newsam. I am glad to have Ming-Hsuan Yang and Trevor Darrell on my PhD committee. My research interests mainly focus on large-scale video analysis, such as human action recognition, video semantic segmentation, optical flow/disparity estimation, surveillance anomaly detection, geo-event discovery etc. Before coming to Merced, I got my EE Master degree from University of Kansas in 2014.

Google Scholar Github

Recent News

09/2018: Three ACCV 2018 papers are accepted.

08/2018: Extend Fall internship at Nvidia applied deep learning research team.

07/2018: Our work on generating ground level views from satellite imagery is covered by MIT technology review, Internet of Business, GIS Lounge, DeepTech. We also had an interview with This Week in Machine Learning & AI.

06/2018: Gave a talk about the winning solution of stereo matching in Robust Vision Challenge (ROB 2018) at CVPR 2018, on behalf of Zhengfa Liang. The video recordings of my talk can be found here.

06/2018: Successfully passed the qualify exam.

05/2018: Start Summer internship at Nvidia applied deep learning research team.

04/2018: Two ICIP 2018 papers are accepted.

02/2018: One CVPR 2018 paper on zero shot action recognition is accepted.

01/2018: Start spring internship at Hikvision Research America.

Professional Activities

Conference Reviewer:

ECCV 2018, BMVC 2018, NIPS 2018, ACCV 2018, AVSS 2018, WACV 2019, ICLR 2019

Journal Reviewer:

Transactions on Pattern Analysis and Machine Intelligence (PAMI), Computer Vision and Image Understanding (CVIU), IEEE Transactions on Image Processing (TIP), Pattern Recognition (PR), IEEE Transactions on Multimedia (TMM), IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), IEEE Transactions on Signal Processing (TSP), IEEE Transactions on Wireless Communication (TWC), Pervasive and Mobile Computing (PMC)

Technical Program Committee:

AVSS 2018


Publications & Preprints

14. Xueqing Deng, Yi Zhu and Shawn Newsam, What Is It Like Down There? Generating Dense Ground-Level Views and Image Features From Overhead Imagery Using Conditional Generative Adversarial Networks

ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL) 2018 (Oral) PDF

13. Yi Zhu, Yang Long, Yu Guan, Shawn Newsam, Ling Shao, Towards Universal Representation for Unseen Action Recognition

Computer Vision and Pattern Recognition (CVPR) 2018 PDF

12. Yi Zhu and Shawn Newsam, Learning Optical Flow via Dilated Networks and Occlusion Reasoning

IEEE International Conference on Image Processing (ICIP) 2018 PDF

11. Xueqing Deng, Yi Zhu and Shawn Newsam, Spatial Morphing Kernel Regression For Feature Interpolation

IEEE International Conference on Image Processing (ICIP) 2018 PDF

10. Yi Zhu, Xueqing Deng, Shawn Newsam, Fine-Grained Land Use Classification at the City Scale Using Ground-Level Images

arXiv preprint arXiv:1802.02668 2018 PDF

9. Yi Zhu, Sen Liu and Shawn Newsam, Large-Scale Mapping of Human Activity using Geo-Tagged Videos

ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL) 2017 PDF

8. Yi Zhu and Shawn Newsam, DenseNet for Dense Flow

IEEE International Conference on Image Processing (ICIP) 2017 (Oral) PDF

7. Yi Zhu, Zhenzhong Lan, Shawn Newsam and Alexander G Hauptmann, Hidden Two-Stream Convolutional Networks for Action Recognition

Asian Conference on Computer Vision (ACCV) 2018 PDF CODE

arXiv preprint arXiv:1704.00389 2017 PDF CODE

6. Yi Zhu, Zhenzhong Lan, Shawn Newsam and Alexander G Hauptmann, Guided Optical Flow Learning

Computer Vision and Pattern Recognition (CVPR) 2017 Workshop PDF CODE

5. Zhenzhong Lan, Yi Zhu, Alexander G Hauptmann and Shawn Newsam, Deep Local Video Feature for Action Recognition

Computer Vision and Pattern Recognition (CVPR) 2017 Workshop (Oral) PDF

4. Yi Zhu and Shawn Newsam, Efficient Action Detection in Untrimmed Videos via Multi-Task Learning

IEEE Winter Conference on Applications of Computer Vision (WACV) 2017 (Oral) PDF

3. Yi Zhu and Shawn Newsam, Spatio-Temporal Sentiment Hotspot Detection using Geotagged Photos

ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL) 2016 PDF

2. Yi Zhu and Shawn Newsam, Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition

European Conference on Computer Vision (ECCV) 2016 Workshop (Oral) PDF SUPP

1. Yi Zhu and Shawn Newsam, Land Use Classification using Convolutional Neural Networks Applied to Ground-Level Images

ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL) 2015 PDF (Best Poster Award)


Challenge & Notebook Papers

Yi Zhu and Shawn Newsam, UC Merced Submission to the ActivityNet Challenge 2016

CVPR 2016 ActivityNet challenge. Untrimmed Video Classification Track. PDF