Diane Larlus

I am a research scientist at the Xerox Research Center Europe (XRCE), in the Textual & Visual Pattern Analysis (TVPA) group. My research interests include machine learning applied to computer vision. I am currently working on semantic image segmentation and document segmentation.

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 XRCE in October 2010.

Research Projects

Publications since I joined Xerox should soon appear here:
XRCE Publication

Selected publication from earlier work:

• Extracting Structures in Image Collections for Object Recognition, S. Ebert, D. Larlus and B. Schiele, European Conference on Computer Vision (ECCV), Crete, Greece, 2010

• Category level object segmentation by combining bag-of-words models with Dirichlet processes and random fields, D. Larlus, J. Verbeek and F. Jurie, International Journal of Computer Vision, Volume 88, Number 2 - jun 2010

• Manifold based local classifiers: linear and non linear approaches, H. Cevikalp, D. Larlus, B. Triggs, M. Neamtu and F. Jurie, Journal of Signal Processing Systems, 61, 1, p 61-73, 2010

• Learning Color Names for Real-World Applications, J. van de Weijer, C. Schmid, J. Verbeek and D. Larlus, IEEE Transactions on Image Processing, jul, Volume 18, Number 7, p.1512–1523, 2009

• Latent mixture vocabularies for object categorization and segmentation, D. Larlus and F. Jurie, Journal of Image & Vision Computing, apr, Volume 27, Number 5, p.523-534, 2009

• Multi-Graph Based Semi-Supervised Learning for Activity Recognition, M. Stikic, D. Larlus and B. Schiele, IEEE International Symposium on Wearable Computers (ISWC'09), 09/2009, Linz, Austria, (2009) Best paper award

• Combining Appearance Models and Markov Random Fields for Category Level Object Segmentation, D. Larlus and F. Jurie, Conference on Computer Vision & Pattern Recognition (CVPR), jun, 2008

• Towards Autonomous Object Reconstruction for Visual Search by the Humanoid Robot HRP-2, O. Stasse, D. Larlus, B. Lagarde, A. Escande, F. Saidi, A. Kheddar, K. Yokoi and F. Jurie, IEEE RAS/RSJ Conference on Humanoids Robot, 2007

• Latent mixture vocabularies for object categorization, D. Larlus and F. Jurie, British Machine Vision Conference (BMVC), 2006