Zhiqiang Tang

Applied Scientist, Amazon Web Service

Email: zhiqiang.tang(at)rutgers.edu

[Scholar] [Github]

About Me

I am an applied scientist at Amazon Web Service. I obtained my Ph.D. degree in Computer Science at Rutgers University–New Brunswick, advised by Prof. Dimitris N. Metaxas.


I work in the areas of machine learning, computer vision, and natural language processing, with particular interests in:

  • Learning from large-scale image, text, and structured data (multimodal learning),

  • Reducing human annotations in training deep neural networks (label efficiency),

  • Lowering the model sensitivity to perturbations (model robustness),

  • Compressing deep models (model efficiency).

Work Experience

03/2021 - Present, Applied Scientist II, Amazon AI, CA, Amazon Web Service (AWS).

06/2020 - 08/2020, Research Intern, Amazon AI, CA, Amazon Web Service (AWS).

06/2019 - 08/2019, Research Intern, IBM AI Research, NY, IBM Thomas J. Watson Research Center.

Selected Publications

CrossNorm and SelfNorm for Generalization under Distribution Shifts.

IEEE International Conference on Computer Vision (ICCV), 2021.

Zhiqiang Tang, Yunhe Gao, Yi Zhu, Zhi Zhang, Mu Li, Dimitris Metaxas.

[Paper] [Code]

OnlineAugment: Online Data Augmentation with Less Domain Knowledge.

In European Conference on Computer Vision (ECCV), 2020.

Zhiqiang Tang, Yunhe Gao, Leonid Karlinsky, Prasanna Sattigeri, Rogerio Feris, and Dimitris Metaxas.

[Paper] [Code & Demo][1min video][10min video]

AdaTransform: Adaptive Data Transformation.

IEEE International Conference on Computer Vision (ICCV), 2019. (Oral)

Zhiqiang Tang, Xi Peng , Tingfeng Li, Yizhe Zhu, and Dimitris Metaxas.


Towards Efficient U-Nets: A Coupled and Quantized Approach.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.

Zhiqiang Tang, Xi Peng , Kang Li, and Dimitris Metaxas.

[Paper] [Code]

Quantized Densely Connected U-Nets for Efficient Landmark Localization.

In European Conference on Computer Vision (ECCV), 2018.

Zhiqiang Tang, Xi Peng , Shijie Geng, Shaoting Zhang, and Dimitris Metaxas.

[Paper] [Code]

CU-Net: Coupled U-Nets.

In British Machine Vision Conference (BMVC), 2018. (Oral)

Zhiqiang Tang, Xi Peng, Shijie Geng, Yizhe Zhu and Dimitris Metaxas.

[Paper] [Code]

Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

Xi Peng*, Zhiqiang Tang*, Fei Yang, Rogerio S Feris, and Dimitris Metaxas.

*contribute equally [Paper] [Code]

A Coupled Hidden Conditional Random Field Model for Simultaneous Face Clustering and Naming in Videos.

IEEE Transactions on Image Processing (TIP), 2016.

Yifan Zhang, Zhiqiang Tang, Baoyuan Wu, Hanqing Lu, and Qiang Ji.


Face Clustering in Videos with Proportion Prior.

International Joint Conference on Artificial Intelligence (IJCAI), 2015. (Long talk)

Zhiqiang Tang, Yifan Zhang, and Hanqing Lu.


Automatic Face Naming in TV Series by Video/Script Alignment.

Neurocomputing, 2015.

Yifan Zhang, Zhiqiang Tang, Chunjie Zhang, Jing Liu, and Hanqing Lu.


Video Face Naming Using Global Sequence Alignment.

International Conference on Image Processing (ICIP), 2014.

Zhiqiang Tang, Yifan Zhang, and Hanqing Lu.