Shiry Ginosar - Homepage

shiry at eecs dot berkeley dot edu
Google Scholar / Twitter

I am a PhD candidate in Computer Vision at the CS Department of the University of California Berkeley working with Professor Alyosha Efros.

Previously I was a Human Computer Interaction researcher. I spent some time as a Visiting Scholar at the CS Department of Carnegie Mellon University, working with Professor Luis von Ahn in the field of Human Computation. More recently, I was part of Professor Bjoern Hartmann's lab at Berkeley. In between I spent four years at Endeca as a Senior Software Engineer.

My work has been covered by The New Yorker, The Wall Street Journal, and the Washington Post among many others. It was exhibited at the Israeli Design Museum and is part of the permanent collection of the Deutsches Museum.

I am a recipient of the U.S. National Science Foundation Graduate Research Fellowship, the California Legislature Grant for graduate studies, the Samuel Silver Memorial Scholarship Award for combining intellectual achievement in science and engineering with serious humanistic and cultural interests and Rising Stars in EECS.


  • speech to gesture translation

    Learning Individual Styles of Conversational Gesture

    Audio to motion translation.
    Human speech is often accompanied by hand and arm gestures. Given audio speech input, we generate plausible gestures to go along with the sound. Specifically, we perform cross-modal translation from ``in-the-wild'' monologue speech of a single speaker to their hand and arm motion. We train on unlabeled videos for which we only have noisy pseudo ground truth from an automatic pose detection system. We release a large video dataset of person-specific gestures.

    Shiry Ginosar*, Amir Bar*, Gefen Kohavi, Caroline Chan, Andrew Owens and Jitendra Malik Learning Individual Styles of Conversational Gesture, CVPR 2019. Project Page, Paper, Video, .
      title={Learning Individual Styles of Conversational Gesture},
      author={Ginosar, Shiry and Bar, Amir and Kohavi, Gefen and Chan, Caroline and Owens, Andrew and Malik, Jitendra},
      journal={Computer Vision and Pattern Recognition (CVPR)},

  • motion retargeting for dance

    Everybody Dance Now!

    "Do as I do" motion transfer.
    Given a source video of a person dancing we can transfer that performance to a novel (amateur) target after only a few minutes of the target subject performing standard moves. We pose this problem as a per-frame image-to-image translation with spatio-temporal smoothing. Using pose detections as an intermediate representation between source and target, we learn a mapping from pose images to a target subject's appearance. We adapt this setup for temporally coherent video generation including realistic face synthesis.

    Caroline Chan, Shiry Ginosar, Tinghui Zhou and Alexei A. Efros Everybody Dance Now, ICCV 2019. PDF, , Video, Project Page

      author = {Chan, Caroline and Ginosar, Shiry and Zhou, Tinghui and Efros, Alexei A.},
      title = "{Everybody Dance Now}",
      journal = {ArXiv e-prints},
      archivePrefix = "arXiv",
      eprint = {1808.07371},
      primaryClass = "cs.GR",
      keywords = {Computer Science - Graphics, Computer Science - Computer Vision and Pattern Recognition},
      year = 2018,
      month = aug,
      adsurl = {},
      adsnote = {Provided by the SAO/NASA Astrophysics Data System}

  • object detections in breughel paintings

    The Burgeoning Computer-Art Symbiosis

    "Computers help us understand art. Art helps us teach computers."

    Shiry Ginosar, Xi Shen, Karan Dwivedi, Elizabeth Honig, and Mathieu Aubry The Burgeoning Computer-Art Symbiosis, XRDS: Crossroads, The ACM Magazine for Students - Computers and Art archive Volume 24 Issue 3, Spring 2018, Pages 30-33. PDF,

      author = {Ginosar, Shiry and Shen, Xi and Dwivedi, Karan and Honig, Elizabeth and Aubry, Mathieu},
      title = {The Burgeoning Computer-art Symbiosis},
      journal = {XRDS},
      issue_date = {Spring 2018},
      volume = {24},
      number = {3},
      month = apr,
      year = {2018},
      issn = {1528-4972},
      pages = {30--33},
      numpages = {4},
      url = {},
      doi = {10.1145/3186655},
      acmid = {3186655},
      publisher = {ACM},
      address = {New York, NY, USA},

  • hair fashions per decade

    A Century of Portraits

    "What makes the 60's look like the 60's?"
    Many details about our world are not captured in written records because they are too mundane or too abstract to describe in words. Fortunately, since the invention of the camera, an ever-increasing number of photographs capture much of this otherwise lost information. This plethora of artifacts documenting our “visual culture” is a treasure trove of knowledge as yet untapped by historians. We present a dataset of 37,921 frontal-facing American high school yearbook photos that allow us to use computation to glimpse into the historical visual record too voluminous to be evaluated manually. The collected portraits provide a constant visual frame of reference with varying content. We can therefore use them to consider issues such as a decade’s defining style elements, or trends in fashion and social norms over time.

    Shiry Ginosar, Kate Rakelly, Sarah Sachs, Brian Yin, Crystal Lee, Philipp Krähenbühl and Alexei A. Efros A Century of Portraits: A Visual Historical Record of American High School Yearbooks, Extreme Imaging Workshop, International Conference on Computer Vision, ICCV 2015. and IEEE Transactions on Computational Imaging, September 2017. PDF, , Project Page

      author={Ginosar, Shiry and Rakelly, Kate and Sachs, Sarah M. and Yin, Brian and Lee, Crystal and Krähenbühl, Philipp and Efros, Alexei A.},
      journal={IEEE Transactions on Computational Imaging},
      title={A Century of Portraits: A Visual Historical Record of American High School Yearbooks},
      keywords={Data mining;Face;Imaging;Market research;Sociology;Statistics;Visualization;Data mining;deep learning;historical data;image dating},

  • object detection in a Picasso image

    Object Detection in Abstract Art

    The human visual system is just as good at recognizing objects in paintings and other abstract depictions as it is recognizing objects in their natural form. Computer vision methods can also recognize objects outside of natural images, however their model of the visual world may not always align with the human one. If the goal of computer vision is to mimic the human visual system, then we must strive to align detection models with the human one. We propose to use Picasso's Cubist paintings to test whether detection methods mimic the human invariance to object fragmentation and part re-organization. We find that while humans significantly outperform current methods, human perception and part-based object models exhibit a similarly graceful degradation as abstraction increases, further corroborating the theory of part-based object representation in the brain.

    Shiry Ginosar, Daniel Haas, Timothy Brown, Jitendra Malik Detecting People in Cubist Art, Visart Workshop on Computer Vision for Art Analysis, European Conference on Computer Vision, ECCV 2014. PDF,

      title={Detecting people in Cubist art},
      author={Ginosar, Shiry and Haas, Daniel and Brown, Timothy and Malik, Jitendra},
      booktitle={Computer Vision-ECCV 2014 Workshops},
      publisher={Springer International Publishing}

  • speech interface for document coding

    Using Speech Recognition in Information Intensive Tasks

    Speech input is growing in importance, especially in mobile applications, but less research has been done on speech input for information intensive tasks like document editing and coding. This paper presents results of a study on the use of a modern publicly available speech recognition system on document coding.

    Shiry Ginosar, Marti A. Hearst, A Study of the Use of Current Speech Recognition in an Information Intensive Task, Workshop on Designing Speech and Language Interactions, ACM Conference on Human Factors in Computing Systems, CHI 2014. PDF

  • multi-stage code examples editor

    Editable Code Histories

    An IDE extension that helps with the task of authoring multi-stage code examples by allowing the author to propagate changes (insertions, deletions and modifications) throughout multiple saved stages of their code.

    Shiry Ginosar, Luis Fernando De Pombo, Maneesh Agrawala, Bjoern Hartmann, Authoring Multi-Stage Code Examples with Editable Code Histories, Proceedings, ACM symposium on User Interface Software and Technology, UIST 2013. (acceptance rate: 19%). PDF, , video

      title={Authoring multi-stage code examples with editable code histories},
      author={Ginosar, Shiry and Pombo, De and Fernando, Luis and Agrawala, Maneesh and Hartmann, Bjorn},
      booktitle={Proceedings of the 26th annual ACM symposium on User interface software and technology},

  • crowdsourced data analysis workflow

    Crowdsourced Data Analysis

    A system that lets analysts use paid crowd workers to explore data sets and helps analysts interactively examine and build upon workers' insights.

    Wesley Willett, Shiry Ginosar, Avital Steinitz, Bjoern Hartmann, Maneesh Agrawala, Identifying Redundancy and Exposing Provenance in Crowdsourced Data Analysis, IEEE Transactions on Visualization and Computer Graphics, 2013. PDF,

      title={Identifying Redundancy and Exposing Provenance in Crowdsourced Data Analysis},
      author={Willett, Wesley and Ginosar, Shiry and Steinitz, Avital and Hartmann, Bjorn and Agrawala, Maneesh},
      journal={Visualization and Computer Graphics, IEEE Transactions on},

  • phetch game logo

    Phetch - A Human Computation Game

    Phetch is an online game which collects natural language descriptions for images on the web as a side effect of game play. Can be used to improve the accessibility of the web as well as improve upon current image search engines.

    Shiry Ginosar, Human Computation for HCIR Evaluation, Proceedings, HCIR 2007, pp. 40-42. PDF

    Luis von Ahn, Shiry Ginosar, Mihir Kedia, Manuel Blum, Improving Image Search with Phetch, Proceedings, International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2007. PDF,

    Luis von Ahn, Shiry Ginosar, Mihir Kedia, Ruoran Liu and Manuel Blum, Improving Accessibility of the Web with a Computer Game, Proceedings, ACM Conference on Human Factors in Computing Systems, CHI 2006, Montreal, Quebec, Canada, April 2006, pp. 79-82. Honorable mentioned paper and nominee for Best of CHI award. PDF, , Press Coverage

      title={Improving accessibility of the web with a computer game},
      author={Von Ahn, Luis and Ginosar, Shiry and Kedia, Mihir and Liu, Ruoran and Blum, Manuel},
      booktitle={Proceedings of the SIGCHI conference on Human Factors in computing systems},

Other Projects

  • H20-IQ device


    A tablet-controlled, solar-powered drip irrigation system. A humidity sensor at the tip of each "spike" records soil moisture; an internal servo in the 3D-printed enclosure opens and closes a drip irrigation line valve. Individual devices in a garden communicate with a central garden server, which also acts as a webserver that hosts the HTML-based user interface. Gardeners can review graphs of humidity readings over time and adjust waterning plans through this Web application.

    Joint class project with Valkyrie Savage and Mark Fuge.

    Featured in Bjoern Hartmann and Paul K. Wright Designing Bespoke Interactive Devices, IEEE Computer August 2013, Volume 46, Number 8. Article


Co-Teacher and GSI, Image Manipulation and Computational Photography, Fall 2018
GSI, Image Manipulation and Computational Photography, Fall 2014

Undergraduate Researchers

Current Undergrads
Varsha Ramakrishnan
Former Undergrads
Gefen Kohavi
Caroline Mai Chan (Now @ MIT)
Hemang Jeetendra Jangle
Daniel Tsai
Crystal Lee
Kate Rakelly (Now @ UC Berkeley)
Brian Yin
Sarah Sachs
Timothy Brown
Luis Fernando de Pombo