Research Grant (“Bolsa de Investigação” ) - Nº016/2021– Deep PCR - PTDC/EEI-COM/1125/2021
|Funding Reference Number:
A research position for one Post Doctoral Research Grant (“Bolsa de Pós Doutoramento”) is open at Instituto de Telecomunicações, in the scope of project “Deep-PCR: Deep learning-based Point Cloud Representation” with Nr/Ref. PTDC/EEI-COM/1125/2021. This project is funded by FCT - Fundação para a Ciência e a Tecnologia.
Information and Data Sciences
Multimedia Signal Processing – Lr
• PhD in computer science, electrical and computer engineering or other relevant area, awarded in the past three years.
• Preference will be given to candidates knowledgeable in machine learning, PC compression and multimedia signal processing.
• Strong motivation to perform research, to participate in a rich and stimulating international project, and to advance state-of-the-art through the publication of results in peer reviewed international conferences and journals.
• Fluent in English and with good skills in technical writing and presenting.
• Good programming skills (Python, C/C++) and knowledge of Deep learning platforms (Tensor Flow, Keras, etc.) are required.
Work Objectives: Visual communications have a fundamental role in Human societies. In the digital era, this has led to the explosion of image and video-based applications and services, notably following the democratization of image and video acquisition, storage and streaming. The recent advances in visual data acquisition and consumption have led to the emergence of the so-called plenoptic visual models, where Point Clouds (PCs) are playing an increasingly important role. PCs are a 3D visual model where the visual scene is represented through a set of points and associated attributes, notably color. To offer realistic and immersive experiences, PCs need to have millions, or even billions, of points, thus asking for efficient coding solutions
Recent years have seen a growing wave of data driven algorithms, such as deep neural networks, which have taken a lead role in many research and development areas, especially in multimedia. This interest is driven by several factors, notably advances in processing power, availability of large data sets, and algorithmic advances. Deep learning (DL)-based solutions are the state-of-the-art for multiple computer vision tasks, both high-level tasks and lower-level tasks. These advances have led to the exploitation of DL-based tools in the image coding domain, reaching competitive performance in a short time. This has been recognized by JPEG (Joint Picture Experts Group) which has just launched the JPEG AI project with the scope of creating a learning-based image coding standard.
The scope of this work is the design, development, implementation and assessment of a DL-based static PC compressed representation targeting both decoding and enhancement consumptions. The DL-based solutions should simultaneously accommodate efficient fidelity-to-original PC coding, with compression efficiency improvements over available solutions, and effective enhanced-from-original PC processing using the same compressed domain stream.
A fellowship will be celebrated according to the regulations defined by FCT, “Regulation of Instituto de Telecomunicações’ fellowships” and “Estatuto do Bolseiro de Investigação”, according to Law no. 123/2019, dated August 28 (Status of Scientific Research Fellow), in its actual redaction, and also by Fundação para Ciência e Tecnologia, I.P. Fellowship Regulation of Fundação para Ciência e Tecnologia. For direct access to the FCT RBI go to the following link https://www.fct.pt/apoios/bolsas/regulamento.phtml.pt (Reg. 950/2019, published in the DR of 16 December).
|Place of work:
The work will be developed at the premises of Instituto de Telecomunicações at Politécnico de Leiria and Instituto Superior Técnico under the supervision of Professors Nuno Rodrigues and Fernando Pereira. The candidates will join a team of staff and PhD students where intense research and development activities in the multimedia signal processing and machine learning fields are carried out.
The research grant is associated to a yearly renewable contract (up to 3 years) that includes an experimental period of 6 months. Start date: 1st January 2022 or soon thereafter
1646,00€ according to the table of grant amounts awarded directly by FCT for positions held in Portugal (www.fct.pt/apoios/bolsas/valores ). The payment will be made by bank transfer.
Candidates may be interviewed for clarification of any aspect related to the above criteria
Each criteria, and the final classification F will be evaluated in a scale (0-20). The candidates will be ordered according to:
F = C1 x 50% + C2 x 40% + C3 x 10%
In case of a tie, the tied candidates will be ordered according to C1, then C2...
The Jury has the right to not admit any of the candidates that applied for this position whenever they consider that no candidate meets the minimum requirements for the position.
|Communication of the results:
Results will be published at the Instituto de Telecomunicações, in Leiria. The selected candidate will be notified by email.
Motivation letter explaining the interest in the position, Detailed Curriculum Vitae with transcripts and recommendation letter(s) (optional), degree certificate. Apply online clicking on the “Apply Now” button in this form.
After the notification of the results, candidates have 10 working days if they wish to contest the decision.
E-mail submissions will not be considered. (The cover letter and the CV are mandatory documents in the online application platform)
NOTICE: Degrees obtained abroad are recognized by a Portuguese higher education institution under the terms of Decree-Law No. 66/2018, of August 16 and Ordinance No. 33/2019, of January 25. More information at: https://www.dges.gov.pt/pt/pagina/reconhecimento?plid=374
All the selection process is conducted through the IT web portal. No actions outside this platform are valid.
29-11-2021 to 15-12-2021