Internship: Offline tracking

Since our founding, IDEMIA has been on a mission to unlock the world and make it safer through our cutting-edge identity technologies. Our technology leadership makes us the partner of choice for hundreds of governments and thousands of enterprises in over 180 countries, including some of the biggest and most influential brands in the world. In applying our unique expertise in biometrics and cryptography, we enable our clients to unlock simpler and safer ways to pay, connect, access, identify, travel and protect public places – at scale and in total security.

Our teams work from 5 continents and speak 100+ different languages. We strongly believe that our diversity is a key driver of innovation and performance.

This role is responsible for design, development and improvement of algorithms to efficiently answer to business or customer needs.

• The internship focuses on Offline Multi-Object Tracking (MOT) for Pedestrians. The student will conduct a thorough study of the state-of-the-art (SOTA) MOT methods, reproduce their results, and explore ways to enhance them. Offline tracking processes the entire video sequence after it has been recorded, unlike online tracking, which makes tracking decisions frame by frame in real time. This allows offline tracking to leverage future frames for better data association, reduce identity switches, and achieve higher overall accuracy in multi-object tracking. 

  
  
  

  Key references include AllTracker, CoTracker3, SAM3, and SAM2MOT. Emphasis will be placed on recent advances in point tracking and segmentation, leveraging foundational models such as SAM3 to improve accuracy and robustness. Point trackers are algorithms that follow specific keypoints or feature points of an object across video frames, rather than tracking the object, using a bounding box. They are particularly useful for capturing fine-grained motion, improving robustness to occlusions, and enhancing object association in multi-object tracking. 

  
  
  

  The intern will experiment, benchmark algorithms, and propose potential improvements to SOTA methods, producing both code and analysis for the research team. 

  
  

We are looking for a highly motivated intern with the following profile: 

 Education: 

 Engineering student in a top-tier school (École Polytechnique, Mines, Centrale-Supelec, Telecom, EPITA or equivalent) in the final year of the engineering cycle, or an M2 university student specializing in deep learning and computer vision. 

 Technical Skills:

• Strong knowledge of image processing, computer vision, and deep learning (preferably with PyTorch).
• Solid foundation in mathematics and data analysis. 
• Proficiency in Python (C/C++ is a plus).
• Experience with image processing libraries is a plus. 

 Soft Skills and Languages: 

• Curious, proactive, and autonomous.
• Results- and solution-oriented.
• Clear and persuasive communication.
• Fluent in English (spoken and written); additional language is a plus.
• Motivation to contribute to the full pipeline of an algorithm: design, implementation, integration, testing, optimization. 

By choosing to work at IDEMIA, you will join a unique tech company, offering a wide range of growth opportunities. You will contribute to a safer world, collaborating with an international and global community. We value the diversity of our teams and welcome people from all walks of life, regardless of how they look, where they come from, who they love, or what they think.

We deliver cutting edge, future proof innovation that reach the highest technological standards and we're transforming, fast, to stay a leader in a world that's changing fast, too.

At IDEMIA, people can develop their expertise and feel a sense of ownership and empowerment, in a global environment, as part of a company with the ambition and the ability to change the world.

Visit our website to know more about the leader in Identity Technologies