Section: Partnerships and Cooperations

International Initiatives

Inria Associate Teams Not Involved in an Inria International Labs

  • Title: Semantic and Geometric Models for Video Interpretation

  • International Partner (Institution - Laboratory - Researcher):

    • Carnegie Mellon University (United States) - Robotics Institute - Deva Ramanan

  • Start year: 2016

  • See also: https://team.inria.fr/gaya/

  • The primary goal of the associate team GAYA is to interpret videos, in terms of recognizing actions, understanding the human-human and human-object interactions. Despite several years of research, it is yet unclear what is an efficient and robust video representation to attack this challenge. In order to address this, GAYA will focus on building semantic models, wherein we learn the video feature representation with limited supervision, and also geometric models, where we study the geometric properties of object shapes to better recognize them. The team consists of researchers from two Inria project-teams (Thoth and WILLOW) and a US university (Carnegie Mellon University [CMU]). It will allow the three teams to effectively combine their respective strengths in areas such as inference and machine learning approaches for vision tasks, feature representation, large-scale learning, geometric reasoning. The main expected outcomes of this collaboration are: effective learnt representations of video content, new machine learning algorithms for handling minimally annotated data, large-scale public datasets for benchmarking, theoretical analysis of objects shapes and contours. In 2017, Gunnar Sigurdsson (PhD student of Abhinav Gupta [CMU]) visited the Thoth team to develop a new dataset of first- and third-person videos and an approach for learning a joint representation of these two modalities.

Inria International Partners

Informal International Partners
  • University of Edinburgh: C. Schmid collaborates with V. Ferrari, full professor at university of Edinburgh. Vicky Kalogeiton started a co-supervised PhD in 2013 and graduated in 2017; she has been bi-localized between Uni. Edinburgh and Inria. Her subject is automatic learning of object representations in videos. The collaboration resulted in two joint publications in 2017 [19], [18].

  • MPI Tübingen: C. Schmid collaborates with M. Black, a research director at MPI, starting in 2013. End of 2015 she was award a Humbolt research award funding a long-term research project with colleagues at MPI. She spent one month at MPI in May 2017. In 2017 the project resulted in the development of a large-scale synthetic human action dataset [12].

  • University of Washington: Julien Mairal collaborates with Zaid Harchaoui, former member of the Lear team, on the topic of large-scale optimization. They co-advised one student, Hongzhou Lin, who defended his PhD in 2017.

Participation in Other International Programs

  • Indo-French project EVEREST with IIIT Hyderabad, India, funded by CEFIPRA (Centre Franco-Indien pour la Promotion de la Recherche Avancee). The aim of this project between Cordelia Schmid, Karteek Alahari and C. V. Jawahar (IIIT Hyderabad) is to enable the use of rich, complex models that are required to address the challenges of high-level computer vision. The work plan for the project will follow three directions. First, we will develop a learning framework that can handle weak annotations. Second, we will build formulations to solve the non-convex optimization problem resulting from the learning framework. Third, we will develop efficient and accurate energy minimization algorithms, in order to make the optimization computationally feasible.