Position

I am a PhD student in the LEAR team of the LJK laboratory and INRIA Rhône-Alpes research center. My doctoral school is the Grenoble INP institute of technology. I am funded by the Microsoft Research-INRIA joint center. I mainly work in the fields of computer vision and machine learning.

I come from the ENSIMAG engineering school of IT and applied Mathematics. I also have a Master's degree in Machine Learning from the Université Joseph Fourier (UJF) of Grenoble.

PhD Thesis

On the 1st of october 2008, I started my PhD thesis under the supervision of the head of the LEAR team: Cordelia Schmid. The title of my PhD subject is:

Learning visual events and actions from natural videos with various levels of supervision

This PhD thesis addresses visual event and action recognition in natural videos, a problem which receives increasing attention due to the widespread availability of personal video capture devices, low cost of multimedia storage and ease of content sharing. The goal is to develop video representations, learning and recognition techniques that would allow to go beyond basic human action classification in simplistic videos, addressing a wider range of visual events and handling real-world multimedia data.

This approach is challenging, as it requires careful consideration of the amount and cost of supervision. Development of learning techniques that can work in semi-supervised or weakly-supervised setups and are able to utilize low-quality supervision is foreseen to be crucial for the success.

Challenges

I participated in two challenges during the 2008 summer period:

Master thesis

Between February and June 2008, I did my Master's internship in the LEAR team with Marcin Marszalek and Cordelia Schmid. My subject was action recognition in videos.

© 2008-2011   Adrien GAIDON