I am a researcher (chargé de recherche) in the Inria Thoth team (previously known as LEAR), based at the Grenoble – Rhône-Alpes center. I was a postdoctoral fellow in the Inria WILLOW project-team at the Department of Computer Science, École Normale Supérieure (ENS), before this, where I worked with Ivan Laptev, Jean Ponce, and Josef Sivic. I completed my Ph.D. in July 2010, under the supervision of Philip Torr. I am also an associate member of the Visual Geometry Group, University of Oxford and the WILLOW team at ENS.
My current research focuses on addressing the visual understanding problem in the context of large-scale video and image datasets. In particular, I work on modeling problems, such as pose estimation, recognition, tracking, segmentation, as optimization problems defined on graphs, learning parameters of the optimization functions with minimally-annotated data, and developing inference algorithms that scale-up to large data collections.