Hi, I'm Zhenyu Wu (CV).

I am a Senior Machine Learning Engineer II (Perception) at Cruise LLC, reporting to Dr. Annie Liu.
I was a researcher at Wormpex AI Research, where I was extremely fortunate to work with Dr. Zhou Ren, Dr. Gang Hua, and Dr. Yi Wu.
I obtained my Ph.D. from VITA Lab, advised by Prof. Atlas Wang.
wuzhenyusjtu AT gmail.com

Education


Research Interests


  • Building practical perception systems that are: (a) robust to perturbations/degradations and distribution shifts; (b) efficient for both inference and training; (c) ethical for individual privacy and group fairness.
  • Solving low-level and high-level vision problems that include: (a) dehazing and image enhancement; (b) object detection and action detection; (c) text spotting; (d) pose estimation; (e) tracking.

Selected Publications

SOAR: Scene-debiasing Open-set Action Recognition
Yuanhao Zhai, Ziyi Liu, Zhenyu Wu, Yi Wu, Chunluan Zhou, David Doermann, Junsong Yuan, and Gang Hua
IEEE ICCV 2023
PDF Code
A Multi-purpose Real Haze Benchmark with Quantifiable Haze Levels and Ground Truth
Priya Narayanan, Zhenyu Wu*, Xin Hu*, Matthew D Thielke, John G Rogers, Andre V Harrison, John A D'Agostino, James D Brown, Long P Quang, James R Uplinger, Heesung Kwon, and Zhangyang Wang
IEEE TIP 2023
PDF Code
Self-supervised Pretraining with Classification Labels for Temporal Activity Detection
Kumara Kahatapitiya, Zhou Ren, Haoxiang Li, Zhenyu Wu, Michael S Ryoo, and Gang Hua
AAAI 2023
PDF Code
TxVAD: Improved Video Action Detection by Transformers
Zhenyu Wu, Zhou Ren, Yi Wu, Zhangyang Wang, and Gang Hua
ACM MM 2022
PDF Code
Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study
Zhenyu Wu, Zhaowen Wang, Ye Yuan, Jianming Zhng, Zhangyang Wang, and Hailin Jin
ACM TOMM 2021
PDF Code
MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis
Zhenyu Wu*, Duc Hoang*, Shih-Yao Lin, Yusheng Xie, Liangjian Chen, Yen-Yu Lin, Zhangyang Wang, and Wei Fan
ACM MM 2020
PDF Code
Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset
Zhenyu Wu*, Haotao Wang*, Zhaowen Wang, Hailin Jin, and Zhangyang Wang
IEEE TPAMI 2020
PDF Code
Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach
Zhenyu Wu, Karthik Suresh, Priya Narayanan, Hongyu Xu, Heesung Kwon and Zhangyang Wang
IEEE ICCV 2019
PDF Code
All-In-One Underwater Image Enhancement using Domain-Adversarial Learning
Pritish Uplavikar, Zhenyu Wu, and Zhangyang Wang
CVPR Workshop 2019
PDF Code
Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
Zhenyu Wu, Zhangyang Wang, Zhaowen Wang, and Hailin Jin
Springer ECCV 2018
PDF Code Adobe News TAMU CSE News
Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
Junru Wu, Yue Wang, Zhenyu Wu, Zhangyang Wang, Ashok Veeraraghavan, and Yingyan Lin
ICML 2018
PDF Code

Challenge Awards


Low-Power Computer Vision Challenge: UAV Video Track
1st Prize
ICCV 2021
PDF Code Slides Certificate
Low-Power Computer Vision Challenge: UAV Video Track
2nd Prize
CVPR 2020
PDF Code

Professional Experience & Activity


Internships

Professional Services:


Invited Talks:

  • Tutorial: Efficient Computer Vision for Embedded Systems (Design Automation Conference 2022)
  • Winner's Talk: Low-Power Computer Vision Challenge: (International Conference of Computer Vision 2021)
  • Winner's Talk: Low-Power Computer Vision Challenge: (Computer Vision and Patter Recognition 2020)
  • Winner's Talk: Chalearn LAP Inpainting Competition (European Conference on Computer Vision 2018)

2022 Zhenyu Wu. Powered by Shuai Yang