Yuliang Zou

Research Scientist
Applied Research Team
Waymo LLC
ylzou [at] waymo [dot] com

About

Bio

I am a Research Scientist at Waymo (formerly the Google self-driving car project).

I received my Ph.D. degree in Computer Engineering at Virginia Tech, working with Prof. Jia-Bin Huang. Before that, I have worked with Prof. Honglak Lee, Yuting Zhang and Ruben Villegas during my masters at University of Michigan, Ann Arbor, and Prof. Xiaojin Gong during my undergrad at Zhejiang University.

Over the summers, I am fortunate to have the opportunities to work with Wei-Chih (Wayne) Hung (Waymo Research), Jyh-Jing Hwang (Waymo Research), Zizhao Zhang (Google Cloud AI), Han Zhang (Google Brain), Chun-Liang Li (Google Cloud AI), Xiao Bian (Google Cloud AI), Pan Ji (NEC Labs), Quoc-Huy Tran (NEC Labs), Prof. Manmohan Chandraker (NEC Labs & UCSD), Jimei Yang (Adobe Research), Duygu Ceylan (Adobe Research), Jianming Zhang (Adobe Research), and Federico Perazzi (Adobe Research).

My CV is available here (last updated on Oct. 2022).

Me in 2016

Education

Aug. 2017 - May. 2022

Aug. 2015 - Apr. 2017

Sep. 2011 - Jun. 2015

Industry

May. 2021 - Aug. 2021

May. 2020 - Aug. 2020

May. 2019 - Aug. 2019

May. 2018 - Aug. 2018

Teaching

Teaching Assistant     

ECE 5554 / ECE 4554 (Computer Vision), Fall 2018 [link]

Teaching Assistant     

ECE 5554 / ECE 4554 (Computer Vision), Fall 2017 [link] [tutorial] [Guest Lecture on Object Detection]

Professional Activities

Conference Reviewer     

CVPR 2019-2023, ICML 2019, 2021, 2023, ICCV 2019-2021, BMVC 2019-2021, NeurIPS 2019-2022, AAAI 2020, 2022, ECCV 2020-2022, ACCV 2020, WACV 2021-2022, ICLR 2021-2023

Journal Reviewer     

TPAMI, IJCV, IET Computer Vision, Neurocomputing, Computer Graphics Forum

Workshop Reviewer     

AI City Challenge Workshop 2018, 2019

Student Volunteer     

ICLR 2020, NeurIPS 2020

Presentations

[2021/11]     

Tech talk at Facebook AI, Virtual

[2021/11]     

Tech talk at Cruise AI Research, Virtual

[2021/10]     

Tech talk at Toyota Research Institute, Virtual

[2021/08]     

"Designing Pseudo Labels for Semantic Segmentation" at Waymo Machine Learning Reading Group, Virtual

[2021/06]     

"Label-Efficient Visual Understanding with Consistency Regularization" at CVPR Doctoral Consortium 2021, Virtual

[2020/11]     

"PseudoSeg: Designing Pseudo Labels for Semantic Segmentation" at Google Cloud Vision/Video Meetup, Virtual

[2020/03]     

"Reducing Footskate in Human Motion Reconstruction with Ground Contact Constraints" at WACV2020, Aspen, Colorado [Slides] [Video]

[2018/09]     

"iCAN: Instance-Centric Attention Network" at 1st Person in Context (PIC) Workshop, Munich, Germany [Slides]

News

[2022/11]     

One paper has been accepted to Computer Vision and Image Understanding!

[2022/07]     

One paper has been accepted to ECCV 2022!

[2022/04]     

I have passed my Ph.D. defense!

[2021/07]     

I receive the Pratt Fellowship from the Bradley Department of Electrical and Computer Engineering, Virginia Tech.

[2021/06]     

I am selected to participate the Doctoral Consortium in CVPR 2021! And my mentor is Prof. Noah Snavely!

[2021/01]     

One paper has been accepted to ICLR 2021!

[2020/12]     

I have passed my preliminary exam today!

[2020/10]     

Thanks Google Cloud for supporting my research with $120,000 GCP credits.

[2020/08]     

Receive the outstanding reviewer award from BMVC 2020!

Publications


Learning Instance-Specific Adaptation for Cross-Domain Segmentation

Panoptic Segmentation Semantic Segmentation Test-Time Adaptation Transfer Learning

Yuliang Zou, Zizhao Zhang, Chun-Liang Li, Han Zhang, Tomas Pfister, Jia-Bin Huang

In Proceedings of the 17th European Conference on Computer Vision (ECCV), 2022.

[arXiv] [Code] [Project Page]

Learning Representational Invariances for Data-Efficient Action Recognition

Action Recognition Data Augmentation Semi-Supervised Learning

Yuliang Zou, Jinwoo Choi*, Qitong Wang, Jia-Bin Huang
(* corresponding author)

Computer Vision and Image Understanding (CVIU), 2022.

[arXiv] [Code] [Project Page]


PseudoSeg: Designing Pseudo Labels for Semantic Segmentation

Semantic Segmentation Semi-Supervised Learning

Yuliang Zou, Zizhao Zhang, Han Zhang, Chun-Liang Li, Xiao Bian, Jia-Bin Huang, Tomas Pfister

In Proceedings of the 9th International Conference on Learning Representations (ICLR), 2021.

[arXiv] [Code] [Poster] [Project Page]

Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling

Sequential Learning Unsupervised Learning Visual Odometry

Yuliang Zou, Pan Ji, Quoc-Huy Tran, Jia-Bin Huang, Manmohan Chandraker

In Proceedings of the 16th European Conference on Computer Vision (ECCV), 2020.

[arXiv] [Project Page]

DRG: Dual Relation Graph for Human-Object Interaction Detection

Graph Network Scene Understanding

Chen Gao, Jiarui Xu, Yuliang Zou, Jia-Bin Huang

In Proceedings of the 16th European Conference on Computer Vision (ECCV), 2020.

[arXiv] [Code] [Project Page]

Reducing Footskate in Human Motion Reconstruction with Ground Contact Constraints

Human Sensing

Yuliang Zou, Jimei Yang, Duygu Ceylan, Jianming Zhang, Federico Perazzi, Jia-Bin Huang

In Proceedings of the 20th Winter Conference on Applications of Computer Vision (WACV), 2020.

[Code] [Data] [Paper] [Poster] [Project Page] [Video]

DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency

Depth Estimation Optical Flow Unsupervised Learning

Yuliang Zou, Zelun Luo, Jia-Bin Huang

In Proceedings of the 15th European Conference on Computer Vision (ECCV), 2018.

[arXiv] [Code] [Poster] [Project Page]

iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection

Object Detection Scene Understanding

Chen Gao, Yuliang Zou, Jia-Bin Huang

In Proceedings of the 29th British Machine Vision Conference (BMVC), 2018

[arXiv] [Code] [Project Page]

Label-Efficient Learning of Transferable Representations across Domains and Tasks

Domain Adaptation Semi-Supervised Learning Transfer Learning

Zelun Luo, Yuliang Zou, Judy Hoffman, Li Fei-Fei

In Proceedings of the 31st Neural Information Processing Systems (NeurIPS), 2017

[arXiv] [Poster] [Project Page]

Learning to Generate Long-term Future via Hierarchical Prediction

Generative Modeling Video Analysis

Ruben Villegas, Jimei Yang, Yuliang Zou, Sungryull Sohn, Xunyu Lin, Honglak Lee

In Proceedings of the 34th International Conference on Machine Learning (ICML), 2017

[arXiv] [Code] [Poster] [Project Page] [Slides] [SOHU News (Chinese)]

Misc

Relevant Courses Taken

CS6804 - Causal Reasoning [website]

CS5834 - Urban Computing [website]

STAT5444 - Bayesian Statistics [website]

ECE5454 - Optimization Techniques

CS5984 - Deep Learning

EECS442 - Computer Vision

EECS498 - Information Retrieval

EECS551 - Matrix Methods

EECS542 - Advanced Topics in Computer Vision

EECS545 - Machine Learning

EECS598 - Random Matrix Theory

CSE - Numerical Method

ISEE - Fundamentals of Information Theory

ISEE - Fundamentals of Digital Video and Audio

cs294a - Unsupervised Feature Learning and Deep Learning [website]

cs231n - Convolutional Neural Networks for Visual Recognition [website]

ee364a - Convex Optimization I [website]

cs236 - Deep Generative Models [website]

GAMES203 - 3D Reconstruction and Understanding [website]

ChM015x - Sensor Fusion and Non-linear Filtering for Automotive Systems (Ongoing) [website]

ML-4340 - Self-Driving Cars (Ongoing) [website]

About My Name

My given name is Yuliang (瑜亮), which comes from two famous characters in the Three Kingdoms. And my family name is Zou (邹).

My English name is Zack. You can also call me Y.L. Anyway, call whatever you like. :)

"欲买桂花同载酒,终不似,少年游。"