First International Workshop on Brave New Ideas For Motion Representations Call for Papers

*******************************************************************************
First International Workshop on Brave New Ideas For Motion Representations
                           BNMW@ECCV16

                 http://bravenewmotion.github.io/

                     Amsterdam, October, 2016

                  in conjunction with  ECCV 2016

            Submission Papers (max 4 pages): August 12, 2016
            Notification of acceptance     : September 02, 2016
            
*******************************************************************************


CALL FOR PAPERS

In the late years Deep Learning has been a great force of change on
most Computer Vision and Multimedia tasks. In video analysis problems,
however, such as action recognition and detection, motion analysis and
tracking, shallow architectures remain surprisingly competitive. What
is the reason for this conundrum?  Larger datasets are part of the
solution. The recently proposed Sports1M helped recently in the
realistic training of large motion networks. Still, the breakthrough
has not yet arrived.

Assuming that the recently proposed video datasets are large enough
for training deep networks for video, another likely culprit for the
standstill in video analysis is the capacity of the existing deep
models. More specifically, the existing deep networks for video
analysis might not be sophisticated enough to address the complexity
of motion information. This makes sense, as videos introduce an
exponential complexity as compared to static images. Unfortunately,
state-of-the-art motion representation models are extensions of
existing image representations rather than motion dedicated
ones. Brave, new and motion-specific representations are likely to be
needed for a breakthrough in video analysis.

Brave new ideas require novel insights. For this reason at this
workshop we have confirmed the availability of several experts from
different fields that relate to the understanding and modelling of
motion and sequence data: a) from Computer Vision Dr. I. Laptev,
Research Director at INRIA Paris-Rocquencourt and a leading expert in
action recognition, b) from Machine Learning Prof. M. Welling at the
University of Amsterdam, a leading expert in variational methods and
Bayesian modelling, c) from Neuroscience, Dr. Aman Saleem, Senior
Researcher at the University College London, working on the
integration of motion and locomotion in the visual cortex of mammals.

INSTRUCTIONS

Attempting to publish a wild, but intriguing idea in Computer Vision
and Multimedia conferences can be daunting, resulting in slow
progress. On one hand a controversial new idea might be rejected by
top-tier conferences, without the right experimental justification.
On the other hand, researchers may not want to reveal a smart idea too
soon in the fear of not receiving the right credit. To make amends
with these two factors, the workshop will admit maximum 4-page papers
describing novel, previously unseen ideas without necessarily
requiring exhaustive quantitative justifications. Moreover, to make
sure proper accreditation is given in the future, the workshop will
have an open-review process, where all submitted papers should first
be uploaded to arXiv.

The workshop's goal is a constructive, creative and open
conversation. In principle we will accept all papers. All reviews will
be made publicly available. Reviewers can choose to remain anonymous
or to reveal their identity to encourage collaboration and positive
feedback. We include poster presentations and will select a few of the
best and bravest papers for an oral presentation.

- The paper length is limited to a maximum 4 pages

- All papers should use provided latex format or similar text
processing tool (download template:
http://users.cecs.anu.edu.au/~basura/workshop/latex_format.zip)

- The papers should present new ideas, not already accepted in prior
conferences.

- The papers will be submitted through arXiv, so that author's work
will be credited.

- The papers will be reviewed via ``Open access review'' at $URL

TOPICS

The workshop focuses on motion representations related, but not
limited, to the following topics:

- Influence of motion in object recognition, object affordance, scene understanding.
- Object and optical flow
- Motion prediction, causal reasoning and forecasting
- Event and action recognition 
- Spatio-temporal action localization
- Modeling human motion in videos and video streams
- Motion segmentation and saliency
- Tracking of objects in space and time
- Unsupervised action, actom discovery using ego motion
- Applications of motion understanding and video dynamics in sports,
  healthcare, autonomous driving, driver assistance and robotics

TENTATIVE SCHEDULE

Time             Event (Topic)
9.30 - 9.35        Welcome to the workshop
9.35 - 10.20    Invited speaker - Professor Max Welling
	 (Motion and Unsupervised learning)
10.20 - 10.35    Coffee break/Poster session (Poster session 1)
10.35 - 11.20    Invited speaker - Dr. Aman Saleem
	 (Motion from a Neuroscience perspective)
11.20 - 11.35    Oral paper 1 [Prize 1] (1st brave new idea)
11.35 - 11.50    Oral paper 2 [Honor. mention] (2nd brave new idea)
11.50 - 13.00    Lunch (on your own)    (Poster session)
13.00 - 13.45    Invited speaker - Professor Ivan Laptev
	 (Computer Vision and motion representations)
13.45 - 14.00    Coffee Break/Poster session
14.00 - 14.45    Invited speaker 4 (Motion representations from signal processing perspective)
14.45 - 15.00    Conclusion/Summary
	 (A summary of the workshop and the related literature)
15.00 - 17.00    Poster session

IMPORTANT DATES

Submission Deadline: August 12, 2016
Notification of acceptance: September 2, 2016
Camera ready version: September 9, 2016
Workshop: One full day among 8th, 9th, 16th October 2016


WORKSHOP ORGANIZERS

Basura Fernando, The Australian National University, Australia
(basura.fernando@anu.edu.au)

Efstratios Gavves, University of Amsterdam, The Netherlands
(egavves@uva.nl)

Jan van Gemert, Delft University of Technology, The Netherlands
(j.c.vangemert@tudelft.nl)

For more information: http://bravenewmotion.github.io/