Reading Systems Engineer Position

October 22, 2021 at 8:33 am by

Reference: 22102021_IRS_engineer

 

About CVC:

The Computer Vision Center (CVC) is a non-profit research center established in 1995 by the Generalitat de Catalunya and the Universitat Autònoma de Barcelona (UAB). Its mission is to carry out cutting-edge research that has the highest international impact in the field of computer vision. It also promotes the transference of knowledge to industry and society.

Computer vision is an exciting research area and an omnipresent technology, essentially empowering machines with the sense of vision. The CVC is a successful marriage between knowledge and innovation. In addition to our cutting-edge scientific achievements, we have established lasting ties with industrial partners and created several spin-off companies.

Research area or group: IRS – Intelligent Reading Systems

 

Description of group/project:

Reading systems deal with replicating in machines the human capacity to extract and understand written communication through vision. Traditionally developed within the document image analysis domain, reading systems have steadily expanded to real scene images, as the man-made world is full of semantically important, written information.

Stemming from the document image analysis domain, the host research group has highlighted the fact that image text, when available, is an important source of information that should be incorporated in computer vision tasks. Reading systems have been incorporated in tasks at the borderline between vision and language such as image captioning and visual question answering, but also in fine-grained classification, cross-modal retrieval and self-supervised learning to mention just a few. In most of these systems the act of “reading” is delegated to a black box recognizer which is assumed correct for the purpose of the higher-level task.

 

Context and Mission:

IRS group is seeking for an engineer to become a member of a larger team of researchers working for the research project “ReadQA: Reading systems for Visual Question Answering” (PID2020-116298GB-I00), funded by the Ministerio de Ciencia e Innovación.

 

The selected candidate will contribute in the following project tasks:

  • Support for the creation and management of annotated datasets
  • Contribute in research tasks related to semantic multimodal analysis
  • Contribute in research tasks related to multilingual VQA
  • Contribute in research tasks related to visual question generation

 

Requirements:

  • MSc – Computer Vision (final thesis topic on reading systems will be highly valued).
  • The candidate must be an effective communicator, multitask, and work well on collaborative and interdisciplinary designs.
  • Ability to think creatively.
  • Ability to work independently and make decisions.
  • Ability to take initiative, prioritize and work under set deadlines and pressure.

 

Conditions:

  • The position will be located at Computer Vision Center (Campus Universitat Autònoma de Barcelona)
  • We offer a 6 months full-time contract, good environment, flexible working hours
  • Salary: 16.074,00 euro gross per year
  • Starting date: ASAP

 

Applications Procedure:

Applicants must submit their curriculum vitae through the application online form, indicating offer code: 22102021_IRS_engineer

 

Selection Procedure:

  1. Pre-selection: determination of compliance with the minimum requirements of the offer.
  2. Selection: assessment of the preselected candidates by scoring based on objective criteria.
  3. Potential candidates will be contacted to set up an interview.

 

Application Deadline: 31/10/2021

­­­­­

Project PID2020-116298GB-I00/ AEI /10.13039/501100011033 funded by Spanish Government – Ministerio de Ciencia e Innovación and Agencia Estatal de Investigación (AEI).


In accordance with current legislation on the Protection of Personal Data, we inform you that your data will be incorporated into a processing under the responsibility of the Computer Vision Center (CVC) in order to manage candidates for the selection process of company personnel. You can find more information in our Privacy Policy.