PhD CIFRE - Multi-task learning for deep-based compressed video processing

InterDigital R&D France, SAS (Rennes, France) Publié il y a 13 jours

About InterDigital 
InterDigital develops mobile and video technologies that are at the core of devices, networks, and services worldwide. We solve many of the industry's most critical and complex technical challenges, inventing solutions for more efficient broadband networks, better video delivery, and richer multimedia experiences years ahead of market deployment. InterDigital has licenses and strategic relationships with many of the world's leading technology companies. Founded in 1972, InterDigital is listed on NASDAQ and is included in the S&P MidCap 400® index.

Job Summary

InterDigital R&I Center in Rennes, France, is looking for a PhD researcher in deep-based video processing. The offer takes place in a project aiming at exploring solutions to limit the energy consumption impact of video coding and distribution. The objective of the PhD thesis is to propose innovative solutions for performing AI-based compressed video enhancement, combining deep neural networks technologies and multi-task learning (MTL) approaches with the perspective of saving energy at the best end-user video quality.

The PhD researcher will develop and implement innovative deep- and MTL-based video processing algorithms, with the aim of assessing and reducing the energy impact of video consumption, through the video distribution chain. The researcher will have opportunities to participate to the external promotion of R&I technologies via contribution to standards, publications, conferences. A high scientific understanding is required in order to execute her/his role in a team of InterDigital experts and in the external scientific community.

The PhD will be executed in two labs, INSA/IETR VAADER team For the academic side, and InterDigital Image & Science Lab for the industrial side.

Responsibilities

The PhD researcher will:

  • Follow-up the state-of-art of published research and standardization in the field of Deep learning, MTL, Video Coding and Energy aware coding.
  • Propose new algorithms for compressed video processing, in collaboration with research team in the field of Video Coding and Deep Learning.
  • Implement algorithms and demonstrate results in conferences and journals.
  • Participate to the research valorization effort through invention disclosures, publications in peered-review journals and conferences.

Profile

  • School Engineer Diploma or Master Degree in computer science with some knowledge and practice in at least one of deep learning, machine learning, signal processing and/or related fields.
  • Interest in Computer Vision and/or image processing and Deep/Machine Learning.
  • Experience in software implementation: C/C++, Windows/Linux, Python, TensorFlow.
  • Team spirit, enthusiastic, motivated, and creative attitude.
  • Good communication skills and ability to present his activities internally and externally,
  • Fluent English mandatory, French appreciated.

InterDigital is committed to a policy of Equal Employment Opportunity and will not engage in or tolerate unlawful discrimination against an applicant or employee on the basis of race, color, religion, creed, national origin, ancestry, citizenship, immigrant status, military status, veteran status, sex, sexual orientation, gender (including gender identity and/or expression), pregnancy, age, physical or mental disability, genetic information, atypical heredity cellular or blood trait, marital status, family status, domestic partner or civil union status or any other legally recognized protected basis under federal, state or local laws, regulations or ordinances. This policy applies to all terms and conditions of employment, including, but not limited to, hiring, compensation, benefits, training, assignments, evaluations, coaching, promotion, discipline, discharge and layoff.  

#LI-DC1

PhD CIFRE - Multi-task learning for deep-based compressed video processing

Postuler sur le site de l'entreprise
Back to search page
;