Baoyuan Wang 王宝元
baoyuanw AT microsoft.com
I am currently a researcher at computational photography team of Microsoft technology and research(TnR) division. My current research interests include computer vision, machine learning, especially using advanced learning techniques to build interesting user preference models for personalization of intelligent captures. In some sense, I'm more like an applied researcher, focus on designing and delivering the most practical techniques for various applications and services for Microsoft. During the past three years, I have been working closely with Natural User Interaction (NUI) team, and successfully shipped several important learning techniques to Xbox One. Recently, my major focus is shipping AI technology to Microsoft Pix cameras. Prior to my current position, I was a lead researcher at Microsoft Research Asia from July 2012 to June 2015.
I got my Ph.D degree at College of Computer Science in Zhejiang University 2012. My advisor is 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. I visited Microsoft Research San Francisco for three months in 2011, under the supervision of LiYi Wei. From Sep. 2006 to Apr. 2007, I was a developer intern at Infosys Limited, Bangalore India.
Vision and Learning Papers
1. Yuanming Hu, Baoyuan Wang, Steve Lin. FC^4:Fully Convolutional Color Constancy with Confidence-weighted Pooling. Accepted by CVPR 2017.
2. Bo Xin, Yizhou Wang, Wen Gao, and Baoyuan Wang, David Wipf. Maximal Sparsity with Deep Networks? NIPS 2016.
3. Huan Yang, Baoyuan Wang, Steve Lin, David Wipf, Baining Guo. Unsupervised Extraction of Video Highlights via Robust Recurrent Auto-Encoders. ICCV'15, Santiago, Chile. [ Paper ] [BibTex]
4. Ruobing Wu, Baoyuan Wang, Yizhou Yu. Harvesting Discriminative Meta Objects with Deep CNN Features for Scene Classification. ICCV'15, Santiago, Chile.
5. Jun Zhu, Baoyuan Wang, Zhuowen Tu. "Action Recognition with Acton". ICCV 2013, Sydney, Australia.
6.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.
7. Xinggang Wang, Baoyuan Wang, Xiang Bai, Zhuowen Tu. "Max-Margin Multiple-Instance Dictionary Learning". ICML 2013, Atlanta, USA.
8. 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.
9. Weijia Zou, Baoyuan Wang, Rui Zhang. "Human Activity Recognition by Mining Discriminative Segment with Novel Skeleton Joint Feature". PCM'13, Oral.
10. Min Tan, Baoyuan Wang, Gang Pan. Robust Object Recognition via Weakly Supervised Metric and Template Learning. Accepted by Neurocomputing, May, 2015.
11. Min Tan, Baoyuan Wang, Zhaohui Wu, Jingdong Wang, Gang Pan. Weakly Supervised Metric Learning for Traffic Sign Recognition in a LIDAR Equipped Vehicle. Accepted by IEEE Transaction on Intelligent Transportation Systems. 2015.
Intelligent Photo Editing Papers
1. Zhicheng Yan, Hao Zhang, Baoyuan Wang, Sylvain Paris, Yizhou Yu. Automatic Photo Adjustment Using Neural Networks. Accepted by ACM Transaction on Graphics. To be presented at SIGGRAPH 2016.
2. Baoyuan Wang, Yizhou Yu, Ying-Qing Xu. "Example-based Image Color and Tone Style Enhancement". (Accepted by SIGGRAPH 2011).
3. Baoyuan Wang, Yizhou Yu, Tien-Tsin Wong, Chun Chen, Ying-Qing Xu. "Data-Driven Image Color Theme Enhancement". SIGGRAPH Asia 2010, Seoul, December 2010 (ACM Transactions on Graphics, Vol. 29, No. 5, 2010). [ More ]
GPGPU and Information Visualization
1. Baoyuan Wang, Yizhou Yu "Parallel H-Tree Based Data Cubing on Graphics Processors", International Journal of Software and Informatics (IJSI), 2012.
2. 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 ]
3. 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.
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.
ACM Transaction on Multimedia, Reviewer
IEEE Transaction on Image Processing, Reviewer
SIGGRAPH 2014 Reviewer
SIGGRAPH Asia 2015 Reviewer
SIGGRAPH Asia 2014 Reviewer
SIGGRAPH Asia 2013 Reviewer
SIGGRAPH Asia 2012 Reviewer
SIGGRAPH Asia 2011 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, Reviewer
ICCV 2017, Reviewer
I3D'2017, PC member.