InternDeep-Based Energy-Aware Video Adaptation H/F

Job description

Description

In this internship, the objective is to design a deep learning model to build energy-aware videos. Methods for building energy-aware images, that is, images that will consume less than their corresponding original versions, while displayed on screen, already exist in the literature. However, they do not take into account the temporal information in videos and thus could lead to temporal inconsistency. The goal is to build a model that will leverage the video information to both ensure temporal consistency and improve performance in terms of quality and energy consumption, compared to frame-based methods. This work shall be seen as one step forward towards a more sustainable video streaming chain. Indeed, in the context of climate change, video streaming shall take part in the challenge of reducing our carbon emissions. The goal will be to find and review potential existing solutions for ensuring temporal consistency in the video processing chain. In a second step, a deep learning-based model will be designed and implemented, to construct energy-aware videos. Evaluation of the performance of the developed model will also be conducted. The internship will take place in the Media Services research group of the InterDigital Video Lab. The intern will be mentored by scientists and will be part of a research project developing solutions to mitigate energy consumption in the video streaming industry. Duration: 5-6 months, starting January-April 2026 Responsibilities State-of-the-art and analysis of existing solutions Implementation of a video-based deep learning model for energy reduction Evaluation and reporting of results Related work [1] O. Le Meur, C. -H. Demarty and L. Blonde, "Deep-Learning-Based Energy Aware Images," 2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia, 2023, pp. 590-594, doi: 10.1109/ICIP49359.2. [2] Ameur, Z., Demarty, CH., Ménard, D., Meur, O.L. (2025). 3R-INN: How to Be Climate Friendly While Consuming/Delivering Videos?. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision - ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15133. Springer, Cham. https://doi.org/10.1-3\_9 [3] Emmanuel Sampaio, Claire-Hélène Demarty, and Olivier Le Meur. 2024. How to make images less power-hungry: An objective benchmark study. In Proceedings of the Second International ACM Green Multimedia Systems Workshop (GMSys '24). Association for Computing Machinery, New York, NY, USA, 1-7. https://doi.org/10.1145/36521 Keywords: energy-aware images, temporal consistency, energy consumption, energy reduction, vision quality metrics, machine learning (deep learning). Expected Outcomes: Apart from the expected outcome that corresponds to the energy-aware video model and its evaluation, this internship will be expected to generate patents and publications. Location: Rennes, France Mentors: Claire-Helene Demarty, Ali Ak InterDigital is an equal employment opportunity employer. InterDigital will not engage in or tolerate unlawful discrimination with regard to any employment decision, policy or practice based on a person's sex, gender, pregnancy (including childbirth, breastfeeding and related medical conditions), age, race, color, religion, creed, national origin, ancestry, citizenship, military status, veteran status, mental or physical disability, medical condition, genetic information, sexual orientation, gender identity or expression, or any other factor protected by applicable federal, state or local law. This policy applies to all terms and conditions of employment, including, but not limited to, recruiting, hiring, compensation, benefits, training, assignments, evaluations, coaching, promotion, discipline, discharge and layoff.

Date de début

24 oct., 2025

Profil

List minimum required qualifications, preferred skills, abilities, experience, and education Master 2 Deep learning. Image and video processing. Python. PyTorch.

Répartition du temps de travail

Full time

Durée (Mois)

6

Formation

RJ/Qualif/Ingenieur_B5

Secteur

Ind_hightech_telecom