Diane Larlus

  • machine learning
  • deep learning
  • computer vision
  • data analytics
  • artificial intelligence

I am a senior research scientist in the Computer Vision group. My research focuses on applying machine learning to several computer vision tasks. I am particularly interested in getting a semantic and global understanding of visual scenes. I have recently worked on instance-level and semantic visual search. I am also interested in representing the structure and geometry of object categories, and in reasoning at the scene-level with images and text.


  • 1 paper accepted at ICCV 17:
  • Learning 3D Object Categories by Looking Around Them (oral presentation)
  • CVPR 17 best reviewer award



  • 2017/2018 - Comprendre des données visuelles à grande échelle (Cours ENSIMAG, Grenoble, France -  5MMDVGE7 - Filière MMIS) 
  • 2016/2017 - Comprendre des données visuelles à grande échelle (Cours ENSIMAG, Grenoble, France -  5MMDVGE7 - Filière MMIS)

Current and past collaborations

  • Andrew Zisserman and Andrea Vedaldi, from the University of Oxford, around object recognition (UAC, 2011-2014),
    I am now jointly supervising David Novotny (since 2015) with Andrea Vedaldi.
  • Svetlana Lazebnik, from the University of Illinois at Urbana-Champaign (UAC, 2013-2016)
  • Sabine Süsstrunk, from EPFL, around scene understanding using visible and near-infrared data (UAC, then Open Innovation project, 2010 to 2013)

Short Bio

I obtained a M.Sc. in Image, Vision and Robotics from UJF/INP, Grenoble, France, in 2005. From 2005 to 2008, I worked as a doctoral candidate in the LEAR group, at INRIA Grenoble. During the summer 2007, I did an internship at the JRL/AIST laboratory in Tsukuba, Japan. I obtained my Ph.D. in 2008, from INP Grenoble. From 2008 to 2010, I worked as a post-doc at TU Darmstadt, Germany. I joined what has now become NAVER LABS Europe in 2010.

+33 (0)4 76 61 50 67