Shugao Ma


Research Scientist [CV]
Facebook Reality Labs
Email: shugao -at- fb.com


About

I am a research scientist at the Facebook Reality Labs (FRL) Pittsburgh. Before joining FRL, I achieved my Ph.D degree in the Computer Science Department of Boston University, during which I was in the Image and Video Computing (IVC) group, advised by Prof. Stan Sclaroff . From 2006 to 2009, I worked on computer vision with Prof. Weiqiang Wang in the JDL in the Chinese Academy of Sciences, where I received my Master's degree. In 2006, I received Bachelor's Degree in Software Engineering from the Fudan University (China) and also Bachelor's Degree in Computer Sciences from the University College Dublin (Ireland).

News

  • We released the large scale motion captured social interaction dataset TalkingWithHands32M
  • Two IJCV journal papers and one Pattern Recognition journal paper are published in Spring of 2017.
  • We release the large scale web action image datasets BU101 and BU203 .
  • One new paper accepted in CVPR 2016 on the topic of LSTM model for activity detection and early detection.
  • I joined Facebook Oculus Research and work with Prof. Yaser Sheikh in Spring of 2016.
  • Oral talk on Space-Time Tree Ensemble for Action Recognition in CVPR 2015.
  • Media coverage of our work Space-Time Tree Ensemble for Action Recognition on Communications of the ACM and Phys.org
  • Summer 2015, internship in Disney Research at Pittsburgh.
  • Our work on Hierarchical Space-Time Segments is well covered in the book Computer Vision in Sports - Springer.
  • Spring 2014, internship in Disney Research at Pittsburgh working with Dr. Leonid Sigal .
  • Summer 2013, internship in Google at Mountain View working on machine learning system for video advertising.


Conference Publications

Chaitanya Ahuja, Shugao Ma, Louis-Philippe Morency, Yaser Sheikah. "To React or not to React: End-to-End Visual Pose Forecasting for Personalized Avatar during Dyadic Conversations". In International Conference on Multimodal Interaction (ICMI), 2019. [PDF]

Gilwoo Lee, Zhiwei Deng, Shugao Ma, Takaaki Shiratori, Siddhartha S. Srinivasa, Yaser Sheikh. "Talking With Hands 16.2M: A Large-Scale Dataset of Synchronized Body-Finger Motion and Audio for Conversational Motion Analysis and Synthesis". In IEEE International Conference on Computer Vision (ICCV), 2019. [PDF] [Dataset]

Aayush Bansal, Shugao Ma, Deva Ramanan, Yaser Sheikh. "Recycle-GAN: Unsupervised Video Retargeting". In European Conference on Computer Vision (ECCV), 2018. [PDF] [Project] [Code]

Shugao Ma , Leonid Sigal and Stan Sclaroff. "Learning Activity Progression in LSTMs for Activity Detection and Early Detection". In conference on Computer Vision and Pattern Recognition (CVPR), 2016. [PDF]

Shugao Ma , Leonid Sigal and Stan Sclaroff. "Space-Time Tree Ensemble for Action Recognition". In conference on Computer Vision and Pattern Recognition (CVPR), oral, 2015. [PDF] [Slides][Project]

Jianming Zhang Shugao Ma , Mehrnoosh Sameki, Stan Sclaroff, Margrit Betke, Zhe Lin, Xiaohui Shen and Brian Price.. "Salient Object Subitizing". In conference on Computer Vision and Pattern Recognition (CVPR), 2015. [PDF]

Svebor Karaman, Lorenzo Seidenari, Shugao Ma , Alberto Del Bimbo and Stan Sclaroff. "Adaptive Structured Pooling for Action Recognition". In British Machine Vision Conference (BMVC), 2014. [PDF]

Jianming Zhang, Shugao Ma , and Stan Sclaroff. "MEEM: Robust Tracking via Multiple Experts using Entropy Minimization". In European Conference on Computer Vision (ECCV), 2014. [PDF][Project]

Shugao Ma, Jianming Zhang, Nazli Ikizler-Cinbis and Stan Sclaroff. "Action Recognition and Localization by Hierarchical Space-Time Segments". In IEEE International Conference on Computer Vision (ICCV), 2013. [PDF][Project]

Shugao Ma, Nazli Ikizler-Cinbis and Stan Sclaroff "Unsupervised learning of discriminative relative visual attributes". In 2nd International Workshop on Parts and Attributes, held in conjunction with European Conference on Computer Vision (ECCV), 2012. [PDF][Slides][code]

Shugao Ma, Weiqiang Wang. "Effective Camera Motion Analysis Approach". In IEEE International Conference on Networking, Sensing and Control (ICNSC), 2010. [PDF]

Shugao Ma, Weiqiang Wang, Shuqiang Jiang, Qingming Huang, Wen Gao. "Effective Scene Matching with Local Feature Representatives". In International Conference on Pattern Recognition (ICPR), 2008 [PDF]



Journal Publications

Jianming Zhang, Shugao Ma, Mehrnoosh Sameki, Stan Sclaroff, Margrit Betke, Zhe Lin, Xiaohui Shen, Brian Price & Radomír Měch "Salient Object Subitizing". in International Journal of Computer Vision (IJCV), 2017.

Shugao Ma , Jianming Zhang, Leonid Sigal, Nazli Ikizler-Cinbis and Stan Sclaroff. "Space-Time Tree Ensemble for Action Recognition". in International Journal of Computer Vision (IJCV), 2017.

Shugao Ma , Sarah Adel Bargal, Jianming Zhang, Leonid Sigal and Stan Sclaroff. "Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web". Pattern Recognition, 2017. [arXiv][Datasets]

Shugao Ma, Weiqiang Wang. "Effective Fighting Shot Discrimination in Action Movie ." Journal of Computer Science and Technology (JCST), Vol.26, No.1, pp.187-19, 2011. [PDF]