Multi-view re-identification of objects and individuals based on 3D representation H/F

Job description: Many monitoring applications, like pedestrian video protection, farm cow monitoring, or team sports analysis, rely on accurate re-identification in camera networks. While re-identification based on appearance details like color and texture has shown good results, the task becomes more complex when recognizing individuals from different viewpoints due to changes in resolution, pose, and lighting. Otherwise, recent advances in 3D object reconstruction offer impressive results. These new representations of individuals are valuable for re-identification based on 3D understanding. With this internship, we would like to explore the extension of this research on 3D representations for re-identification, to the use of multiple views of the same object or individual. Different approaches can be explored during the intership : • Exploiting multiple images as query or gallery for re-identification during training or inference. • Explore the concept of multiple view fusion in a unique re-identification representation enriched by each point of view. • Explore the fusion of 2D images as an implicit multi-view re-id representation vs a more explicit 3D representation leveraging SOTA 3D reconstruction approaches from one or many images More details on https://kalisteo.cea.fr/index.php/apply-for-a-job/

Institute description: Based in Saclay (Essonne), the LIST is one of the two institutes of CEA Tech, the Technological Research Division of the CEA. Dedicated to intelligent digital systems, its mission is to carry out technological developments of excellence on behalf of industrial partners, in order to create value. Within the LIST, the Laboratory of Vision and Learning for Scene Analysis (LVA) conducts its research in the field of computer vision and artificial intelligence for the perception of intelligent and autonomous systems. The laboratory's research themes include visual recognition, behavior and activity analysis, large-scale automatic annotation, and perception and decision models.utilisées dans l'industrie française et européenne de demain.

Your profile: Qualifications • Students in their 5th year of studies (M2) • Computer vision skills • Machine learning skills (deep learning, LLM, VLM, generative AI...) • Python proficiency in a deep learning framework (especially PyTorch or TensorFlow) Job-related benefits Join CEA List and LVA as an intern to: • Work in one of the most innovative research organizations in the world, addressing societal challenges to build the world of tomorrow • Discover a rich ecosystem: privileged connections between the industrial and academic sectors • Conduct research autonomously and creatively: encouragement to valorize results (scientific articles, patents, open-source codes...) • Join a young and dynamic team • Benefit from an internal computing infrastructure with more than 300 state-of-the-art GPUs • Receive a stipend between €1300 and €1400 per month • Have the opportunity to continue with a PhD or as a research engineer after the internship • Have the possibility of remote work, receive a 75% reimbursement on public transportation costs, and benefit from the “mobili-jeune” aid to reduce rent costs... In line with CEA's commitment to integrating people with disabilities, this job is open to all.

Level of qualification studied: Bac+5 - Master of Science

Languages: English Intermediate