Yixin Gao

I am a Ph. D. candidate in Department of Computer Science at the Johns Hopkins University, where I focus on machine learning and pattern discovery from complex time series data, such as surgical kenimatic and video data. My adivsors are Prof. Sanjeev Khudanpur and Prof. Gregory Hager.

Before joining Hopkins, I obtained my master's and bachelor's degrees in electrical engineering from Xi'an Jiaotong University, where I worked with Prof. Guizhong Liu on image/video data compression and unified speech and audio coding schemes.

I will join Amazon Alexa team after I finish my PhD.

Here are my resume and my LinkedIn profile.

Research Interests

Machine learning (deep learning, graphical models, sequence learning), Automatic speech recognition, Natural language processing, Computer vision, Robotics, etc


  • Machine Learning Scientist Intern (10/2016 - 01/2017), Amazon, Boston, MA
  • I worked on the Alexa Speech Recognition.
  • Data Scientist Intern (05/2016 - 08/2016), Intuitive Surgical, Sunnyvale, CA
  • I worked on clustering mehtods on event sequence data from the da Vinci surgical system.
  • Data Scientist Consultant (08/2015 -), LINKSciences, Baltimore, MD
  • I have been volunteering as a Data Scientist Consultant for the local startup LINKSciences, where I helped design the strategy for data mining from large scale public datasets.
  • Teaching Assisitant (09/2013 - 05/2016), Department of Computer Science, Johns Hopkins Unviersity
  • I learned (and re-learned!) courses through teaching assistantship, and won the Excellent Teaching Award! Cousese I TAed:
    Introduction to algorithms
    Algorithms for sensor-based robotics
    Computational theory and automata
    Information retrieval and web agents.
  • Research Assisitant (01/2012-), CIRL Lab, Johns Hopkins Unviersity
  • I am a member of the Language of Surgery team in Malone Center for Engineering in Healthcare, where I work on my PhD thesis on unsupervised learning for surgical pattern and structure discovery, which involves:
    Learning efficient representations for surgical data
    Aligning surgical activities
    Query-by-example surgical activity detection.
    Temporal pattern discovery in surgical motion
    Besides, I have also worked on side projects:
    Improving surgical activity classification by combining HMM with VQ, and developed an C++ HMM toolkit
    Managing and releasing the JIGSAWS dataset for public research
  • Research Assisitant (09/2009 - 12/2011), VISR Lab, Johns Hopkins Unviersity
  • I began my fun years at Hopkins on super hands-on robotics projects where I obtained experiences with hardwares and system development:
    Cross-platform surgical training and evaluation.
  • Research Assisitant (09/2006 - 07/2009), SIGPRO Lab, Xi'an Jiaotong University
  • I spent three exciting years at Xi'an Jiaotong University working on source coding of multimedia data and was an organizing volunteer during VIE2008. Projects I have accomplished:
    Unified speech and audio coding
    Biorthogonal frequency-varying modulated lapped transform
    ROI-based error resilient coding of H.264

    Selected Publications

  • Narges Ahmidi, Lingling Tao, Shahin Sefati, Yixin Gao, Colin Lea, Benjamın Bejar Haro, Luca Zappella, Sanjeev Khudanpur, Rene Vidal, Gregory D. Hager, A Dataset and Benchmarks for Segmentation and Recognition of Gestures in Robotic Surgery, Transaction of Biomedical Engineering, 2017.
  • Yixin Gao, S Swaroop Vedula, Gyusung Lee, Mija Lee, Sanjeev Khudanpur and Gregory D Hager, Query-by-Example Surgical Activity Detection, International Journal of Computer Assisted Radiology and Surgery, 2016
  • Yixin Gao, S Swaroop Vedula, Gyusung Lee, Mija Lee, Sanjeev Khudanpur and Gregory D Hager, Unsupervised Surgical Signal Align- ment with Application to Automatic Activity Annotation, IEEE International Conference on Robotics and Automation (ICRA) 2016
  • S. Swaroop Vedula, Anand O. Malpani, Lingling Tao, George Chen, Yixin Gao, Piyush Poddar, Narges Ahmidi, Christopher Paxton, Rene Vidal, Sanjeev Khudanpur, Gregory D. Hager, Chi Chiung Grace Chen, Analysis of the structure of surgical activity for a suturing and knot-tying task, PLoS ONE 11(3): e0149174. doi:10.1371/journal.pone.0149174
  • Yixin Gao, S Swaroop Vedula, Carol E Reiley, Narges Ahmidi, Balakrishnan Varadarajan, Henry C Lin, Lingling Tao, Luca Zappella, Benjamin Bejar, David D Yuh, Chi Chiung Grace Chen, Rene Vidal, Sanjeev Khudanpur, Gregory D Hager, JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS): A Surgical Activity Dataset for Human Motion Modeling, Fifth Workshop on Modeling and Monitoring of Computer Assisted Interventions (M2CAI), 2014 The JIGSAWS dataset
  • Narges Ahmidi, Yixin Gao, Benjamín Bejar, S Swaroop Vedula, Sanjeev Khudanpur, René Vidal, Gregory D Hager, String Motif-Based Description of Tool Motion for Detecting Skill and Gestures in Robotic Surgery, Medical Image Computing and Computer-Assisted Intervention - MICCAI 26-33, 2013
  • Yixin Gao, Mert Sedef, Amod Jog, Peter Peng, Michael Choti, Gregory Hager, Jeff Berkley, Rajesh Kumar, Towards validation of robotic surgery training assessment across trainng platforms. IEEE Intelligent Robots and Systems (IROS) , 2011
  • Fan Li, Yixin Gao, ROI-based error resilient coding of H.264 for conversational video communication 7th International Conference Wireless Communications and Mobile Computing (IWCMC), pp. 1719-1723, 2011
  • Yixin Gao, Russell H Taylor and Rajesh Kumar, A modular architecture for biomanipulation. 2010 MICCAI workshop on Systems and Architectures for Computed Assisted Intervention, MIDAS Journal (available online http://hdl.handle.net/10380/3195) , Sept. 22 - Sept. 26, 2010
  • Yixin Gao, Guizhong Liu, Biorthogonal frequency-varying modulated lapped transform, Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on pp. 209-212, June 28 - July 3, 2009.
  • Here is my Google Scholar profile.