Connectionists: MOI2QDN Workshop at ICPR2020

[Alexandra Psarrou]

 MOI2QDN Workshop at ICPR2020

International Workshop on Metrification and Optimization of Input Image Quality in Deep Networks (MOI2QDN)

 workshop in conjunction with the
 25th International Conference on Pattern Recognition (ICPR2020)
                      Milan, Italy, January 11, 2021


https://sites.google.com/my.westminster.ac.uk/moi2qdn/home

 P A P E R   S U B M I S S I O N   I S   N O W   O P E N !

     * PLEASE NOTE THAT PAPERS NOT ACCEPTED IN THE ICPR2020 GENERAL *
       SESSION AND FITTING MOI2QDN2020 TOPICS COULD BE SUBMITTED HERE


             *** Submission deadline: October 10, 2020 ***



CALL FOR PAPERS:

Recent years have seen significant advances in image processing and computer vision applications based on Deep Neural Networks (DNNs). Often deep neural networks for such applications are trained and validated based on the assumption that the images are artefact-free. However, in most real-time embedded system applications the images input to the networks, in addition to any variations of external conditions, have artefacts introduced by the Image Signal Processing (ISP) pipelines.

Despite recent advances in interpretability and explainability of deep neural models, DNNs remain widely systems whose operational boundaries cannot be explained or otherwise quantified. It is therefore not clear the level of ISP distortions critical networks can tolerate, or the exact reasons for any performance degradation.

This workshop addresses the issues of performance quantification in DNNs and explore recent advances in the systematic analysis of the performance of deep neural networks with respect to degradations in the input image quality due to the ISP pipeline and their proposed solutions.

Topics of interest include (but are not limited) to:

  *   Case studies investigating the performance of deep neural networks with respect to change in input image quality
  *   Operational boundaries of DNNs with respect to input image quality
  *   Input image quality metrics for deep neural networks
  *   Optimisation of physical camera parameters and ISP pipelines for integrated DNNs embedded systems
  *   Architectural structures of DNNs for optimising integrated ISP embedded systems


PAPER SUBMISSON:


Submissions must be formatted in accordance with the Springer's Computer Science Proceedings guidelines<https://www.google.com/url?q=https%3A%2F%2Fwww.springer.com%2Fgp%2Fcomputer-science%2Flncs%2Fconference-proceedings-guidelines&sa=D&sntz=1&usg=AFQjCNEKfHG_OWF-xZf2IZYd9nHgFBcftQ>.

The following paper categories are welcome:

  *   Full papers (12-15 pages, including references)
  *   Short papers (6-8 pages, including references)

Accepted manuscripts will be included in the ICPR 2020 Workshop Proceedings Springer volume.

Once accepted, at least one author is expected to attend the event and orally present the paper.

Papers can be submitted using Microsoft CMT<https://cmt3.research.microsoft.com/MOI2QDN2021>




DATES:

Paper submission: 10 October 2020

Notification: 10 November 2020

Camera ready: 15 November 2020

Workshop: 11 January 2021



ORGANIZERS:

For any information please sent an email to one of the organisers:

Alexandra Psarrou <psarroa at westminster.ac.uk<mailto:psarroa at westminster.ac.uk>>

Sophie Triantaphillidou <triants at westminster.ac.uk<mailto:triants at westminster.ac.uk>>

Markos Mentzelopoulos <mentzem at westminster.ac.uk>





The University of Westminster is a charity and a company limited by guarantee. Registration number: 977818 England. Registered Office: 309 Regent Street, London W1B 2HW.

This message and its attachments are private and confidential. If you have received this message in error, please notify the sender and remove it and its attachments from your system.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20200706/3a8ba638/attachment.html>