[visionlist] IEEE JSTSP Special Issue on Compact Deep Neural Networks with Industrial Applications

CALL FOR PAPERS
IEEE Journal of Selected Topics in Signal Processing Special Issue on
Compact Deep Neural Networks with Industrial Applications
https://ift.tt/2Uazrwf

Artificial neural networks have been adopted for a broad range of
tasks in areas like multimedia analysis and processing, media coding,
data analytics, etc. Their recent success is based on the feasibility
of processing much larger and complex deep neural networks (DNNs) than
in the past, and the availability of large-scale training data sets.
As a consequence, the large memory footprint of trained neural
networks and the high computational complexity of performing inference
cannot be neglected. Many applications require the deployment of a
particular trained network instance, potentially to a larger number of
devices, which may have limitations in terms of processing power and
memory e.g., for mobile devices or Internet of Things (IoT) devices.
For such applications, compact representations of neural networks are
of increasing relevance.

This special issue aims to feature recent work related to techniques
and applications of compact and efficient neural network
representations. It is expected that these works will be of interest
to both academic researchers and industrial practitioners, in the
fields of machine learning, computer vision and pattern recognition,
media data processing, as well as fields such as AI hardware design
etc. In spite of active research in the area, there are still open
questions to be clarified concerning, for example, how to train neural
networks with optimal performance while achieving compact
representations, and how to achieve representations that do not only
allow for compact transmission, but also for efficient inference.

This special issue therefore solicits original and innovative works to
address these open questions in, but not limited to, following topics:
● Sparsification, binarization, quantization, pruning, thresholding
and coding of neural networks
● Efficient computation and acceleration of deep convolutional neural networks
● Deep neural network computation for low power consumption applications
● Exchange formats and industrial standardization of compact &
efficient neural networks
● Applications e.g. video & media compression methods using compressed DNNs
● Performance evaluation and benchmarking of compressed DNNs

Prospective authors should follow the instructions given on the IEEE
JSTSP webpage: https://ift.tt/2JCxkNO,
and submit their manuscript through the web submission system at:
https://ift.tt/YHx6Zd.

Dates:
Submission deadline: 01-Jun-2019
First Review: 01-Aug-2019
Revisions due: 01-Oct-2019
Second Review: 15-Nov-2019
Final Manuscripts: 10-Jan-2020
Publication: March 2020

Guest Editors:
Diana Marculescu, Carnegie Mellon University, USA
Lixin Fan, JD.COM, Silicon Valley Labs, USA (Lead GE)
Werner Bailer, Joanneum Research, Austria
Yurong Chen, Intel Labs China, China

Advertisements

[visionlist] Call for Papers: Joint Workshop on On-Device Machine Learning & Compact Deep Neural Network Representations (ODML-CDNNR)

Call for Papers: Joint Workshop on On-Device Machine Learning &
Compact Deep Neural Network Representations (ODML-CDNNR)

This joint workshop aims to bring together researchers, educators,
practitioners who are interested in techniques as well as applications
of on-device machine learning and compact, efficient neural network
representations. One aim of the workshop discussion is to establish
close connection between researchers in the machine learning community
and engineers in industry, and to benefit both academic researchers as
well as industrial practitioners. The other aim is the evaluation and
comparability of resource-efficient machine learning methods and
compact and efficient network representations, and their relation to
particular target platforms (some of which may be highly optimized for
neural network inference). The research community has still to develop
established evaluation procedures and metrics.

The workshop also aims at reproducibility and comparability of methods
for compact and efficient neural network representations, and
on-device machine learning. Contributors are thus encouraged to make
their code available.

Topics of interest include, but are not limited to:
. Model compression for efficient inference with deep networks and
other ML models
. Learning efficient deep neural networks under memory and compute
constraints for on-device applications
. Low-precision training/inference & acceleration of deep neural
networks on mobile devices
. Sparsification, binarization, quantization, pruning, thresholding
and coding of neural network
. Deep neural network computation for low power consumption applications
. Efficient on-device ML for real-time applications in computer
vision, language understanding, speech processing, mobile health and
automotive (e.g., . computer vision for self-driving cars, video and
image compression), multimodal learning
. Software libraries (including open-source) optimized for efficient
inference and on-device ML
. Open datasets and test environments for benchmarking inference with
efficient DNN representations
. Metrics for evaluating the performance of efficient DNN representations
. Methods for comparing efficient DNN inference across platforms and tasks

Workshop Website:
https://ift.tt/2JH2jYW
Contact: icml2019-odml-cdnnr@googlegroups.com

Submission Instructions

An extended abstract (3 pages long using ICML style, see
https://ift.tt/2U7CANq ) in PDF
format should be submitted for evaluation of the originality and
quality of the work. The evaluation is double-blind and the abstract
must be anonymous. References may extend beyond the 3 page limit, and
parallel submissions to a journal or conferences (e.g. AAAI or ICLR)
are permitted.

Submissions will be accepted as contributed talks (oral) or poster
presentations. Extended abstract should be submitted through EasyChair
(https://ift.tt/2JEhx0Z). All
accepted abstracts will be posted on the workshop website and
archived.

Selection policy: all submitted abstracts will be evaluated based on
their novelty, soundness and impacts. At the workshop we encourage
DISCUSSION about NEW IDEAS.

Important Dates
Submission: Apr. 7, 2019
Notification: Apr. 24, 2019
Workshop: Jun. 14 or 15, 2019

Workshop organisers
Sujith Ravi, Google Research
Zornitsa Kozareva, Google
Lixin Fan, JD.com
Max Welling, Qualcomm & University of Amsterdam
Yurong Chen, Intel Labs China
Werner Bailer, Joanneum Research
Brian Kulis, Boston University
Haoji (Roland) Hu, Zhejiang University
Jonathan Dekhtiar, Nvidia
Yingyan Lin, Rice University
Diana Marculescu, Carnegie Mellon University


[visionlist] [Vision] Special Issue on “Visual Control of Action” – Last Call

Dear colleagues:

The is the last call for submitting an article in the special
issue on
“Visual Control of Actionâ€
that will be published in
Vision
(https://ift.tt/2CSGHow).

The
deadline for submissions is
*31
March 2019*.

For more details please visit the website:
https://ift.tt/2UtmNoM.
There is
*no
publishing fee*
for this issue.

Feel free to distribute the information.
Thank you and I am looking forward to your submission.

 

Dr. Rebecca M.
Foerster

 

Guest Editors of Special Issue “Visual Control
of Actionâ€

https://ift.tt/2UtmNoM


[visionlist] CAIP 2019 CONTEST on LOCAL IMAGE DESCRIPTORS – submissions OPEN

            ***  submissions for the CAIP 2019 contest  ***

                           Which is Which?

             Evaluation of local descriptors for image
                  matching in real-world scenarios

               


[visionlist] Color & Imaging Conference CFP Closes April 7 – Submit Your Research Today!

Does your research impact the medical field or applications like Virtual Reality and 3D printing, video and film production, or further enhance the study of color science?
Consider sharing your expertise as an oral or interactive paper, in the Journal of Imaging Science and Technology (JIST), or through a short course or workshop.

Your ticket awaits—Submit your research today for the Twenty-seventh
Color and Imaging Conference (CIC27)!

CIC27 | 21-25 October 2019 | Paris, France
http://www.imaging.org/color

TOPICS INCLUDE…
Color Perception: Visual adaptation, visual psychophysics,
color blindness, psychological effects of color…

Capture, Display, and Print: Color imaging sensing, mobile
color imaging, special effects color printing, high dynamic range (HDR)…

Material Appearance and Color: Material capture, 3D
printing, 3D CAD modeling, computer-generated imagery (CGI)…

Specific Color Applications: Cultural heritage applications,
color in cinema and broadcast video, AR/VR/MR, video games…

View the full list of topics and submission details at http://www.imaging.org/color

Journal of Imaging Science and Technology (JIST-first)
Deadline: 24 March 2019

Conference Proceedings Paper
Deadline: 7 April 2019

Connect with our community!
LinkedIn: IS&T CIC Group
Twitter: @ImagingOrg #CIC27 | Subscribe to the Color & Imaging list for news and discussion


[visionlist] REMINDER: abstract submission deadline ECVP 2019 approaching


[visionlist] IGS2019 Call for Posters

International Geometry Summit
2019 – Call for Posters

17-21 June 2019, Vancouver – Canada

https://ift.tt/2ukV3HB

Overview

On 2019, the
IGS2019 International Geometry Summit features 4 major conferences in Computer
Graphics and applications

●     
SPM – Solid and Physical
Modelling

●     
SIAM/GD Computational Geometric
Design

●     
SMI – Shape Modelling
International

●     
GMP- Geometric Modelling and
Processing

IGS2019 seeks poster submissions, which describe recent work,
highly relevant results of work in progress, or successful systems and
applications, in all areas related to

●     
solid and physical modelling

●     
computational geometric design

●     
shape modelling and analysis

●     
geometric modelling and processing

Presenting a
poster is an important way to get feedback on work that has not yet been
published. Poster presentations will be an integral part of IGS2019, with a
joint poster session for interactive discussion between presenters and
attendees, plus a fast-forward presentation track where authors will orally
present a brief summary of their work to all IGS2019 attendees. We require at
least one presenter per accepted poster to attend IGS2019 or one of its 4
conferences.

Submission
Guidelines

Poster
submissions must be in English and include authors names, affiliation, and
contact. The submission must be in the form of a two/four-page abstract, as a
PDF file with embedded fonts, and must be formatted according to the LATEX
guidelines available at the following URL

https://ift.tt/2FlqXJi

Poster abstracts must be submitted by
email to igs2019poster@gmail.com Additional material is not mandatory and can
be shared as a DropBox link or sent by using common FTP services.

Final posters
must be in portrait format with a maximum size given by the A0 standard (841 x
1189 mm, or 33.1 x 46.8 in).

Two/four-page
abstracts will be included in the Poster proceedings.

IGS2019 Poster Chairs &
Contact For more information, please contact the
Posters Chairs igs2019poster@gmail.com

●     
Carolina Beccari (University of Bologna, Italy)

●     
Xin Shane Li (Louisiana State University, USA)

●     
Tao Ju (Washington University, USA)

●     
Giuseppe Patanè (CNR-IMATI, Italy)

Important
Dates

●     
April 22, 2019: Two/four-page abstract and
optional material submission

●     
April 26, 2019: Notification of results

●     
May 13, 2019: Camera-ready material
submission (to be published in IGS2019 Poster Proceedings)

&nbsp