Statistical Deep Learning in Computer Vision (SDL-CV) Call for Papers

It is our pleasure to invite you to submit extended abstracts (4 pages
long excluding references, with optional appendix) for oral and poster
presentations at The First Workshop on Statistical Deep Learning in
Computer Vision (SDL-CV) which will be held in conjunction with ICCV
2019.

We will also invite selected papers for submission to a special issue
on Statistical Deep Learning for Computer Vision in the International
Journal of Computer Vision (IJCV). Extended versions of selected
papers will be invited for book chapter publication.

Submission Deadline: July 31, 2019

Workshop Website: http://www.sdlcv-workshop.com/

Please find the full CfP below.

Kind regards,

Mete Ozay on behalf of the organizers

=== Workshop Description ===

Deep learning has been a useful and primary toolbox to perform various
computer vision tasks successfully in the recent years. Various
seminal works have been proposed to explain the underlying theory and
mechanisms of these successful algorithms, in order to further improve
their various properties, such as generalization capacity of models,
representation capacity of learned features, convergence and
computational complexity of training methods.

In this workshop, we consider statistical approaches employed to
improve our understanding of deep learning, and to develop methods to
boost their properties, with applications in computer vision, such as
object recognition, detection, segmentation, tracking, scene
description, visual question answering, robot vision, image
enhancement and recovery. The workshop will consist of invited talks,
oral talks, poster sessions and a research panel. Our target audience
is graduate students, researchers and practitioners who have been
working on development of novel statistical deep learning algorithms
and/or their application to solve practical problems in computer
vision. Accepted papers will present their results in the workshop in
oral talks and poster sessions. We will also invite selected papers
for submission to a special issue on Statistical Deep Learning for
Computer Vision in the International Journal of Computer Vision
(IJCV). Extended versions of selected papers will be invited for book
chapter publication.

=== Covered Topics ===

We solicit original contributions that deploy statistical deep
learning methods employed to perform various computer vision tasks
including, but not limited to:

- Statistical Understanding of Deep Learning

   -- Interpretable deep learning, quantitative measures and analyses

- Statistical Normalization Methods

  -- Feature, weight, gradient and hybrid normalization methods

- Uncertainty in Deep Learning

  -- Uncertainty measures, adversarial methods, intrinsic and
  extrinsic uncertainty of models

- Information Theory of Deep Learning

   -- Information geometry, information bottleneck, rate distortion,
   etc.

- Probabilistic Deep Learning

  -- Variational methods, graphical methods, Bayesian learning and
  inference

  -- Bayesian deep learning

  -- Neural network architecture search via probabilistic models

- Stochastic Optimization for Deep Learning

  -- Optimization on Riemannian manifolds, topological manifolds, and
  product manifolds

- Probabilistic Programming for Deep Learning

  -- Scene perception, logical reasoning, autonomous driving

- Statistical Meta-learning Algorithms

  -- Few-shot learning/incremental learning for image classification
  and beyond

  -- Zero-shot learning for high-level vision tasks

- Reinforcement Learning for Vision Systems

  -- RL algorithms and vision problems

- Causal Deep Learning

  -- Causal inference, causal feature learning

=== Call for Papers ===

We invite submissions describing works in the domains suggested above
or in closely-related areas. We encourage the submission of previously
published material (clearly marked as such) that is closely related to
the workshop topic. We will invite the best original papers for an
oral plenary presentation. Accepted papers will be presented in
oral/poster sessions at the workshop and appear in the CVF open access
archive. The review process is single-blind. Each paper will receive
strong accept (for oral candidate), accept or reject decision. Note
that there is no author feedback phase during submission. We will also
invite selected papers for submission to a special issue on
Statistical Deep Learning for Computer Vision in the International
Journal of Computer Vision (IJCV). Extended versions of selected
papers will be invited for book chapter publication.

Paper submission deadline: July 31, 2019

Author notification: Sep 4, 2019

Camera-ready deadline: Sep 25, 2019

=== Submission Instructions ===

Format and paper length:

A paper submission has to be in English, in pdf format, and at most
FOUR pages (excluding references). The paper format must follow the
same guidelines as used in the ICCV 2019 submissions. For further
details, please see:

http://www.sdlcv-workshop.com/

=== Invited Speakers ===

We are proud to have a group of diverse invited speakers covering the

entire spectrum of scene and and situation understanding research:

* Xianfeng Gu, Stony Brook University

* Alex Kendall, University of Cambridge

* Yi Ma, University of California, Berkeley

* Yingnian Wu, University of California, Los Angeles

* Alan L. Yuille, Johns Hopkins University

* Lizhong Zheng, Massachusetts Institute of Technology

 === Organizers ===

Ping Luo, HKU

Mete Ozay, PKSHA

Hongyang Li, CUHK

Chaochao Lu, Cambridge University

Lei Huang, IIAI

Wenqi Shao, CUHK

Xianfeng Gu, Stony Brook University

Alan L. Yuille, Johns Hopkins University

Xiaogang Wang, CUHK

Yi Ma, University of California, Berkeley

Lizhong Zheng, MIT