Computer Vision

Pinterest Labs tackles the most challenging problems in Machine Learning and Artificial Intelligence
Learn more
Computer Vision at Pinterest

Pinterest is at the forefront of visual discovery and recommendations development. We recently launched Pinterest Lens, which lets people use their camera phone to get recommendations inspired by objects they see in the real world. Our latest browser extension also gives them recommendations based on images they find on Pinterest, or around the web. So far, we've detected over a billion visual objects, and now serve 250M+ visual searches each month. But there are still many challenging problems yet to be solved in fine grained recognition, object-to-object visual search and large-scale visual search infrastructure. We're also just beginning to experiment with new mediums like video.

Meet the team

Dmitry Kislyuk
Andrew Zhai
Trevor Darrell
Eric Tzeng
Zhiyuan Zhang

  • 1. Visual Discovery at Pinterest

    Team: Andrew Zhai, Dmitry Kislyuk, Yushi Jing, Michael Feng, Eric Tzeng, Jeff Donahue, Yue Li Du, Trevor Darrell
    When: ACM International Conference on World Wide Web (WWW), 2017.
  • 2. Human Curation and Convnets: Powering Item-to-Item Recommendations on Pinterest

    Team: Dmitry Kislyuk, Yuchen Liu, David Liu, Eric Tzeng, Yushi Jing
    When: Arxiv, 2015.
  • 3. Visual Search at Pinterest

    Team: Yushi Jing, David Liu, Dmitry Kislyuk, Andrew Zhai, Jiajing Xu, Jeff Donahue, Sarah Tavel
    When: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2015.