Baoyuan Wang

Email: baoyuanw AT

Affiliations: Co-founder and VP at, a startup spin-off from Microsoft.

Address: Redmond/Beijing


I recently joined Xiaobing.AI, after 12 wonderful years at Microsoft. I will mainly focus on multimodality representation learning for conversational AI, content generation, with the goal of creating AI characters that can not only assist for accomplishing certain tasks but more importantly serve as the long-term companions. Reach out to us if you have passion in working in this space.

I was a principal researcher and manager at AI platform team of Microsoft AI and Cloud. My research interests include computer vision, learning based computational photography and AI for content generation. I always look for addressing industry scale challenges, and keep an eye on practical machine learning settings. Over the years, I have been working closely with different product teams including Bing map, XBox/Kinect, Microsoft Pix Camera, Swift-Key and Cognitive services etc, and shipped several important technologies to those products. Prior to the current position, I was a lead researcher at Microsoft Research Asia lab.

I got my Ph.D degree at College of Computer Science in Zhejiang University 2012. My advisor was Professor Yizhou Yu. I received my B.S. in College of Software Engineering from Zhejiang University in 2007. I was also a research intern at Internet Graphics group, Microsoft Research Asia from May 2009 to June 2012, worked with Ying-Qing Xu. I visited Microsoft Research San Francisco for three months in 2011, under the supervision of LiYi Wei and Jaron Lanier. From Sep. 2006 to Apr. 2007, I was a developer intern at Infosys Limited, Bangalore India.

My latest CV

Preprints and Publications:

1. Noranart Vesdapunt, Mitch Rundle, Muscle Wu, Baoyuan Wang. JNR:Joint-based Neural Rig Representation for Compact 3D Face Modeling. ECCV'2020, AUGUST, UK.

2. Bindita Chaudhuri, Noranart Vesdapunt, Linda Shapiro, Baoyuan Wang. Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting. ECCV'2020, Spotlight , AUGUST, UK.

3. Wenbin Zhu, Muscle Wu, Zeyu Chen, Noranart Vesdapunt, Baoyuan Wang. ReDA: Reinforced Differentiable Attributes for 3D Face Reconstruction. IEEE CVPR 2020, Oral, Seattle, WA.

4. BINDITA CHAUDHURI, Noranart Vesdapunt, Baoyuan Wang. Joint Face Detection and Facial Motion Retargeting for Multiple Faces . IEEE CVPR 2019. 2019.2.26.

5. Gaurav Mittal, Baoyuan Wang. Animating Faces with Disentangled Audio Representation Learning. IEEE WACV 2020.

6. Baoyuan Wang, Noranart Vesdapunt, Utkarsh Sinha, Lei Zhang. Real-time Burst Photo Selection Using a Light-Head Adversarial Net., 2019.11.20, IEEE Transactions on Image Processing (TIP 2020)

7. Huan Yang, Baoyuan Wang, Noranart Vesdapunt, Minyi Guo, Sing Bing Kang. Personalized Exposure Control Using Adaptive Metering and Reinforcement Learning. IEEE Transactions on Visualization and Computer Graphics ( Volume: 25 , Issue: 10 , Oct. 1 2019 )

8. Yuanming Hu, Hao He, Chenxi Xu, Baoyuan Wang, Stephen Lin. Exposure: A White-Box Photo Post-Processing Framework,, ACM Transaction on Graphics, Presented at SIGGRAPH 2018

9. Bin Dai, Baoyuan Wang, Gang Hua. Understanding and Predicting The Attractiveness of Human Action Shot., 2017. 11

10. TaeHyun Oh,Kyungdon Joo, Neel Josh, Baoyuan Wang, Sing Bing Kang. Personalized Cinemagraphs using Semantic Understanding and Collaborative Learning. IEEE ICCV'2017, Venice, Italy.

11. Yuanming Hu, Baoyuan Wang, Steve Lin. FC^4:Fully Convolutional Color Constancy with Confidence-weighted Pooling. IEEE CVPR' 2017, Oral, Honolulu, Hawaii.

12. Bo Xin, Yizhou Wang, Wen Gao, and Baoyuan Wang, David Wipf. Maximal Sparsity with Deep Networks? NIPS 2016.

13. Huan Yang, Baoyuan Wang, Steve Lin, David Wipf, Baining Guo. Unsupervised Extraction of Video Highlights via Robust Recurrent Auto-Encoders. IEEE ICCV'15, Santiago, Chile. [ Paper ] [BibTex]

14. Ruobing Wu, Baoyuan Wang, Yizhou Yu. Harvesting Discriminative Meta Objects with Deep CNN Features for Scene Classification. IEEE ICCV'15, Santiago, Chile.

15. Jun Zhu, Baoyuan Wang, Zhuowen Tu. "Action Recognition with Acton". IEEE ICCV 2013, Sydney, Australia.

16. Yuwang Wang, Baoyuan Wang, Yizhou Yu, Zhuowen Tu. "Action Gons: Action Recognition with A Discriminative Dictionary of Structured Elements with Varying Granularity ", ACCV'14, Singapore.

17. Xinggang Wang, Baoyuan Wang, Xiang Bai, Zhuowen Tu. "Max-Margin Multiple-Instance Dictionary Learning". ICML 2013, Atlanta, USA.

18. Wangjiang Zhu, Baoyuan Wang, Steve Lin. Adaptive Polling on Multiple Trajectory Attributes for Action Recognition. The 12th IEEE International conference on Advanced Video and Signal-based Surveillance (AVSS’15). Oral.

19. Weijia Zou, Baoyuan Wang, Rui Zhang. "Human Activity Recognition by Mining Discriminative Segment with Novel Skeleton Joint Feature". PCM'13, Oral.

20. Min Tan, Baoyuan Wang, Gang Pan. Robust Object Recognition via Weakly Supervised Metric and Template Learning. Accepted by Neurocomputing, May, 2015.

21. Min Tan, Baoyuan Wang, Zhaohui Wu, Jingdong Wang, Gang Pan. Weakly Supervised Metric Learning for Traffic Sign Recognition in a LIDAR Equipped Vehicle. IEEE Transaction on Intelligent Transportation Systems. 2015.

22. Zhicheng Yan, Hao Zhang, Baoyuan Wang, Sylvain Paris, Yizhou Yu. Automatic Photo Adjustment Using Neural Networks. ACM Transaction on Graphics. Presented at SIGGRAPH 2016.

23. Baoyuan Wang, Yizhou Yu, Ying-Qing Xu. "Example-based Image Color and Tone Style Enhancement". ACM SIGGRAPH 2011.

24. Baoyuan Wang, Yizhou Yu, Tien-Tsin Wong, Chun Chen, Ying-Qing Xu. "Data-Driven Image Color Theme Enhancement". ACM SIGGRAPH Asia 2010, Seoul, December 2010 (ACM Transactions on Graphics, Vol. 29, No. 5, 2010). [ More ]

25. Baoyuan Wang, Yizhou Yu "Parallel H-Tree Based Data Cubing on Graphics Processors", International Journal of Software and Informatics (IJSI), 2012.

26. Baoyuan Wang, Gang Chen, Jiajun Bu, Yizhou Yu. "Multiscale Visualization of Relational Databases Using Layered Zoom trees and Partial Data Cubes". International Conference On Information Visualization Theory and Applications (IVAPP), Angers, France, May 2010 (Oral). [ More ]

27. Baoyuan Wang, Gang Chen, Jiajun Bu, Yizhou Yu. "Zoomtree: Unrestricted Zooming Path in Multi-scale Visual Analysis of Relational Databases". Computer Vision, Imaging and Computer Graphics. Theory and Applications. Pages 299-317. 2011.

US Patent

Baoyuan Wang etc. Low-Latency Gesture Detection. 340953.01. This technique has been shipped to XBox/Kinect2.

The following patents are co-invented with other colleagues at MSR, have shipped or are going to ship into Microsoft Pix Camera.

Baoyuan Wang etc. Real-time Exposure Control on Mobile devices.

Baoyuan Wang etc. Generating Semantically Meaningful Video Loops In A Cinemagraph.

Baoyuan Wang etc. Automantic Generation of Semantic-Based Cinemagraphs

Baoyuan Wang etc. Reducing Computational Overhead Via Predications of Subjective Quality Of Automated Image Sequence Processing

Baoyuan Wang etc. Variable Pre-And Post-Shot Continous Frame Buffering With Automated Image Selection And Enhancement

Baoyuan Wang etc. Predicting the Best Photo From a Burst Image Sequence.

Baoyuan Wang etc. Color constancy Via Deep Learning

Academic Services

JMLR Reviewer

IJCV Reviewer

ACM Transaction on Multimedia, Reviewer

IEEE Transaction on Image Processing, Reviewer

SIGGRAPH 2014, 2016, 2018, 2019, 2020, 2021 Reviewer

SIGGRAPH Asia 2011,2012, 2013,2014,2015,2016,2017,2018 Reviewer

PG 2010 Reviewer

PG 2015 Reviewer

TVCG 2013, Reviewer

EG 2011,2012,2015,2016 Reviewer

EGSR 2012 Reviewer

IEEE International Conference on Computer Vision, 2015, Reviewer

CVPR 2016,2017,2018, 2019, 2020, 2021 Reviewer

ICCV 2017, 2019, 2021 Reviewer

ECCV 2020 Reviewer

I3D'2017, PC member.

CAD/Graphics 2019, PC member