Job Specifications
Job description:
Purpose
This role is responsible for design, development and improvement of algorithms to efficiently answer to business or customer needs.
Key Missions
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.
Profile description:
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.
About the Company
As our world becomes increasingly digitally connected, personal identity and security only become more important. That's why protecting the identity of citizens is a top priority of private and public organizations worldwide. As a trusted partner to companies and government agencies for more than 60 years, our deep domain expertise in civil identity, public security, secure credentials, and commercial markets for biometric identification and document authentication is second to none. Our biometrics-based identity platform of...
Know more