Section: Partnerships and Cooperations

International Initiatives

Inria Associate Teams

• HYPERION: Large-scale statistical learning for visual recognition. Inria principal investigator: Zaid Harchaoui. International Partner (Institution - Laboratory - Researcher): University of California Berkeley (United States) - Electrical Engineering and Computer Science Department. Duration: 2012 - 2014. The goal of the associated team “Hyperion” is to take up the challenges of large-scale statistical learning for image interpretation and video understanding. Despite the ever-increasing number of large annotated image and video datasets, designing principled and scalable statistical learning approaches from such big computer vision datasets remains a major scientific challenge.

  The associated team consists of researchers from the LEAR project team of Inria and two teams of University of California Berkeley (resp. the Pr. Jitendra Malik and the Pr. Nourredine El Karoui teams). It allows the three teams to effectively combine their respective strengths in areas such as large-scale learning theory and algorithms, high-level feature design for computer vision, and high-dimensional statistical learning theory. It will result in significant progress in domains such as large-scale image classification, weakly-supervised learning for classification into attributes, and transfer learning.

Inria International Partners

• UC Berkeley: This collaboration between Bin Yu, Jack Gallant, Yuval Benjamini, Adam Bloniarz (UC Berkeley), Ben Willmore (Oxford University) and Julien Mairal (Inria LEAR) aims to discover the functionalities of areas of the visual cortex. We have introduced an image representation for area V4, adapting tools from computer vision to neuroscience data. The collaboration started when Julien Mairal was a post-doctoral researcher at UC Berkeley and is still ongoing. Adam Bloniarz, who is pursuing his PhD under the supervision of Prof. Bin Yu, visited LEAR duing the summer 2013.

• University of Edinburgh: C. Schmid collaborates with V. Ferrari, associate professor at university of Edinburgh. Our initial collaboration (co-supervision of A. Prest 2009-2012) was renewed this year. Vicky Kalogeiton started a co-supervised PhD in September 2013; she is bi-localized between Uni. Edinburgh and Inria. Her subject is the automatic learning of object representations in videos.

• MPI Tübingen: C. Schmid collaborates with M. Black, a research director at MPI. In 2013, she spent one month at MPI and worked with a PhD student, S. Zuffi, and a postdoctoral researcher, H. Jhuang. This resulted in two ICCV'13 publications: one on modeling pose with flexible human puppets [32] and one on measuring the impact of low, intermediate and high-level descriptions on action recognition [22] . C. Schmid plans to continue this collaboration in 2014.

Participation In other International Programs

• France-Berkeley fund: The LEAR team was awarded in 2012 a grant from the France-Berkeley fund for the project with Pr. Jitendra Malik (EECS, UC Berkeley) on "Large-scale learning for image and video interpretation". The award amounts to 10,000 USD for a period of one year, from September 2012 to September 2013. The funds are meant to support scientific and scholarly exchanges and collaboration between the two teams.