About me
My name is Yue Zhao* (赵岳 in simplified Chinese). I am currently a MPhil student at Multimedia Laboratory in the Chinese University of Hong Kong, supervised by Prof. Dahua Lin. I obtained my Bachelor's degree from Tsinghua University. I did some research on biomedical signal processing and speech recognition when I was an undergraduate. My current research interests are in video analysis and understanding.
News
[09/03/2020] Two papers accepted to CVPR 2020 (1 oral + 1 poster).
[02/08/2019] The extended version of our ICCV 2017 work has been accepted by IJCV.
[18/06/2019] We launch MMAction, a versatile toolbox for action understanding based on PyTorch. v0.1.0 is now online!
Education Experience
The Chinese University of Hong Kong, HK SAR
August 2017 - Now
M.Phil. in Information Engineering.
Israel Institute of Technology (Technion), Haifa, Israel
July 2016 - August 2016
Visiting Student of Summer School of Engineering and Science, fully funded by Technion.
Department of Electronic Engineering, Tsinghua University, Beijing, China
August 2012 - July 2016
Bachelor of Engineering, magna cum laude.
School of Economics and Management, Tsinghua University, Beijing, China
August 2013 - July 2016
Bachelor of Science (Second Degree) in Economics.
Department of Information Technology and Electrical Engineering (D-ITET), Swiss Federal Institute of Technology(ETH), Zürich, Switzerland
September 2014 - Feburary 2015
Mobility student fully funded by China Scholarship Council (CSC).
Professional Experience
Multimedia Laboratory, The Chinese University of Hong Kong, HK SAR
September 2016 - August 2017, July 2015 - September 2015
Junior Research Assistant
Publications
Omni-sourced Webly-supervised Learning for Video Recognition
Haodong Duan, Yue Zhao, Yuanjun Xiong, Wentao Liu, Dahua Lin
European Conference on Computer Vision (ECCV), 2020
[arXiv]
[model]
FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding
Dian Shao, Yue Zhao, Bo Dai, Dahua Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (Oral).
[arXiv][project page]
Intra- and Inter-Action Understanding via Temporal Action Parsing
Dian Shao, Yue Zhao, Bo Dai, Dahua Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
[arXiv][project page]
Temporal Action Detection with Structured Segment Networks
Yue Zhao, Yuanjun Xiong, Limin Wang, Zhirong Wu, Xiaoou Tang, Dahua Lin
International Journal on Computer Vision (IJCV), 2020.
[Springer link]
[ICCV17 Version]
[code]
[project page]
Trajectory Convolution for Action Recognition
Yue Zhao, Yuanjun Xiong, Dahua Lin
Thirty-second Conference on Neural Information Processing Systems (NeurIPS), 2018.
[pdf][code]
Find and Focus: Retrieve and Localize Video Events with Natural Language Queries
Dian Shao*, Yu Xiong*, Yue Zhao, Qingqiu Huang, Yu Qiao, Dahua Lin
European Conference on Computer Vision (ECCV), 2018.
[pdf]
[project page]
Recognizing Actions by Disentangling Components of Dynamics
Yue Zhao, Yuanjun Xiong, Dahua Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[pdf]
[supplementary]
Temporal Action Detection with Structured Segment Networks
Yue Zhao, Yuanjun Xiong, Limin Wang, Zhirong Wu, Xiaoou Tang, Dahua Lin
International Conference on Computer Vision (ICCV), 2017.
[pdf]
[arXiv]
[IJCV version]
[code]
[project page]
Recurrent Convolutional Neural Network for Speech Processing
Yue Zhao, Xingyu Jin, Xiaolin Hu
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017.
[pdf]
[code]
[poster]
Heart Rate Estimation in Photoplethysmogram Signals using Nonlinear Model-Based Preprocessing
Federico Wadehn, Yue Zhao, Hans-Andrea Loeliger
IEEE Computing in Cardiology (CinC), 2015.
[pdf]
Manuscripts & Preprints
CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2017
Yue Zhao, Bowen Zhang, Zhirong Wu, Shuo Yang, Lei Zhou, Sijie Yan, Limin Wang, Yuanjun Xiong, Yali Wang, Dahua Lin, Yu Qiao, Xiaoou Tang
CVPR Workshop on ActivityNet Large Scale Activity Recognition Challenge, 2017
[pdf]
Other projects
People tracking using RGB-D videos.
An undergraduate-level class project on people detection and tracking from RGB-D data collected by Kinect. [demo]