Master internship on human action description
During this project the student will start with using and improving
existing software to extract human tracks in videos. The research
question to be address is then: given these human tracks, what is the
best way to represent an action? And how can different types of
actions be captured most efficiently? The project will start with
implementing 3D histogram of gradient descriptors and investigating
how to extend them to be more flexible to variations of
actions. Namely, chaining small chunks of action descriptions with a
conditional random field will be investigated. Validation will be
conducted on real world videos, such as movies.
Your profile:
- Bachelor degree (master1) (preferably in Computer Science or Applied Mathematics; Electrical Engineering will also be considered)
- Solid programming skills; the project involves programming in Matlab and C++
- Solid mathematics knowledge (especially linear algebra and statistics)
- Creative and highly motivated
- Fluent in English, both written and spoken
- Prior knowledge in the areas of computer vision, machine learning or data mining is a plus (ideally a Bachelor thesis in a related field)
Duration: 3 to 6 months
Start date: As soon as possible
Location: This is a project at INRIA Grenoble, Montbonnot.
Contacts:
Res. Dir. Cordelia Schmid, schmid@inrialpes.fr
Please send applications via email, including:
- a complete CV
- graduation marks
- topic of your Bachelor thesis
- the name and email address of two references (including your BS thesis supervisor)
- if you already have research experience, please include a publication list and references