[visionlist] CFP: CVPR 2020 Workshop: Deep Declarative Networks [Extended Submission Deadline]

[Anoop Cherian]

Apologies for cross-posting. We are extending the submission deadline to
20th March 2020. More details below.

Deep Declarative Networks CVPR 2020 Workshop -- Call for Papers
*****************************************************

Website: http://cvpr2020.deepdeclarativenetworks.com/
<https://urldefense.proofpoint.com/v2/url?u=http-3A__cvpr2020.deepdeclarativenetworks.com_&d=DwMFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rStC00sfV_qVWqlcnmGhKrRoTMim5rLso-FTzVW2NfNyo&m=nSaJf4GGDWvvPmYROUEbLOOSoG4UJSFiai5wZ3c0UJw&s=uiU8xfHay6u2ep2H7e2L9gyRN9rykj6ORELL9gxN10o&e=>
Submission Deadline: 20th March 2020
Workshop on 14th June 2020 in conjunction with CVPR 2020, Seattle, WA
Contact us at cvpr2020 at deepdeclarativenetworks.com

*****************************************************

ABOUT
******
Conventional deep learning architectures involve composition of simple
feedforward processing functions that are explicitly defined. Recently,
researchers have been exploring deep learning models with implicitly
defined components, where the output of the node involves solving an
optimization problem in the forward pass. To distinguish these from
conventional deep learning models, we call them deep declarative networks,
borrowing nomenclature from the programming languages community.

This workshop explores the advantages (and potential shortcomings) of
declarative networks and their variants, bringing ideas developed in
different contexts under the umbrella of deep declarative networks. We will
discuss technical issues that need to be overcome in developing such models
and applications of these models to computer vision problems that show
benefit over conventional approaches. For details on the topics, program,
and speakers, please visit http://cvpr2020.deepdeclarativenetworks.com/
<https://urldefense.proofpoint.com/v2/url?u=http-3A__cvpr2020.deepdeclarativenetworks.com_&d=DwMFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rStC00sfV_qVWqlcnmGhKrRoTMim5rLso-FTzVW2NfNyo&m=nSaJf4GGDWvvPmYROUEbLOOSoG4UJSFiai5wZ3c0UJw&s=uiU8xfHay6u2ep2H7e2L9gyRN9rykj6ORELL9gxN10o&e=>

TOPICS
******
We invite paper submissions of up to four (4) pages describing work in
related areas including:
* Declarative end-to-end learnable processing nodes
* Differentiable constrained and unconstrained (non-convex) optimization
problems
* Differentiable convex optimization problems and techniques
* Imposing hard constraints in deep learning models
* Backpropagation through statistical and physics models
* Applications of the above to problems in computer vision, such as
     ** differentiable rendering
     ** differentiable 3d models
     ** reinforcement learning
     ** action recognition
     ** meta-learning, etc.

SUBMISSIONS
************
Accepted submissions will be presented as short orals or posters at the
workshop and will appear on the workshop website. Authors will be given an
opportunity to revise the submission before posting on the website.

Papers should follow the CVPR formatting guidelines and emailed as a single
PDF to cvpr2020 at deepdeclarativenetworks.com, with subject line “Paper: ”.
Submissions are not anonymous (and should include all authors’ names and
affiliations). References are to be included in the 4-page limit. We
encourage submissions of preliminary or ongoing work. Accepted papers
**will not appear** in the official IEEE proceedings. Relevant work that
has previously been published or is to be presented at the main conference
is also welcome.

IMPORTANT DATES
****************
Submission deadline: 20 March 2020
Author Notification: 13 April 2020
Camera-ready deadline: 1 May 2020
Workshop date: 14 June 2020

Organizers: Stephen Gould (ANU), Anoop Cherian (MERL), Dylan Campbell (ANU),
and Richard Hartley (ANU)

Email: cvpr2020 at deepdeclarativenetworks.com
Website: http://cvpr2020.deepdeclarativenetworks.com/
<https://urldefense.proofpoint.com/v2/url?u=http-3A__cvpr2020.deepdeclarativenetworks.com_&d=DwMFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rStC00sfV_qVWqlcnmGhKrRoTMim5rLso-FTzVW2NfNyo&m=nSaJf4GGDWvvPmYROUEbLOOSoG4UJSFiai5wZ3c0UJw&s=uiU8xfHay6u2ep2H7e2L9gyRN9rykj6ORELL9gxN10o&e=>





-- 
Thank you,

Anoop Cherian, PhD
Research Scientist,
Mitsubishi Electric Research Labs,
Cambridge, MA

Phone: +1-313-413-4756
Email: cherian at merl.com
Website: http://users.cecs.anu.edu.au/~cherian/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20200229/dfe00645/attachment.html>