[visionlist] EADS Human Re-Identification Contest deadline extension

The deadline for Phase 1 of EADS “Find Me if you Can” Contest has been postponed to 12th of May to encourage new teams to participate. EADS Innovation Works launched a contest called Join The Spirit 2013 – “Find Me if You Can”.This contest focuses on human re identification in images.
Its main goal is to seek for innovative and efficient algorithmic
approaches solving the following problem: “Given two pictures each
showing a person, can you tell me whether it is the same person or not?â€The contest consists of two distinct phases enabling to reach this objective and to propose a consistent solution from end to end.The 20 top-ranked teams will be approved for the contest’s Phase 2 and awarded from our sponsor Parrot by the Parrot AR.Drone 2.0 remote-control quadrocopter.At end of Phase 2, the team ranked no. 1 on the leaderboard will be declared the winner, earning a VIP-invitation to Astrium space facilities in French Guiana at the occasion of an Ariane 5 launch!Important dates:

The contest opens March 1, 2013 and finishes September 30, 2013 at
midnight (GMT).  The mid-course decision is to occur on May 12, 2013.
The list of finalists from the first phase will be published on the “Join the Spirit†website.
Who can take part? Every graduate or PhD engineering student enrolled in a university, with no limitation of age or countries.More information & Registration at:https://jointhespirit.eads.com/dashboard/openContests

Advertisements

[visionlist] Postdoc position in neurocognitive rehab at Kessler Foundation / New Jersey Medical School


[visionlist] British Congress of Optometry and Vision Science

British Congress of Optometry and Vision Science

Dear Colleagues,

We are pleased to announce that we will be hosting the British Congress of Optometry and Vision Science (BCOVS) on 9/10th September 2013 at Glasgow Caledonian University. This meeting aims to bring together individual researchers and their research groups through a broad range of studies and techniques that reflect the diversity and originality of all aspects of vision research.

This year’s Plenary Lecture will be given by Professor Dennis Levi, UC Berkeley.

Further details can be found at the following http://bcovs2013.eventbrite.com

We would be very grateful if you could forward this information to any interested parties in your respective departments.

We look forward to seeing you in Glasgow in September.

Kind regards
Anita J Simmers

Glasgow Caledonian University is a registered Scottish charity, number SC021474

Winner: Times Higher Education’s Widening Participation Initiative of the Year 2009 and Herald Society’s Education Initiative of the Year 2009.
http://www.gcu.ac.uk/newsevents/news/bycategory/theuniversity/1/name,6219,en.html

Winner: Times Higher Education’s Outstanding Support for Early Career Researchers of the Year 2010, GCU as a lead with Universities Scotland partners.
http://www.gcu.ac.uk/newsevents/news/bycategory/theuniversity/1/name,15691,en.html


[Imageworld] ACII 2013 – DEADLINE EXTENSION for regular papers


[Imageworld] Call For Papers: ICML 2013 workshop—WDDL (Submission deadline is April 6th, 2013)


[Imageworld] CFP: ICML 2013 Workshop on Inferning

Please note that the deadline for submission has been extended to April 20th.

Call For Papers for ICML 2013 Workshop on

Inferning: Interactions between Inference and Learning

June 20-21, 2013
Atlanta, GA
http://inferning.cs.umass.edu
inferning2013@gmail.com

There are strong interactions between learning algorithms which estimate the parameters of a model from data, and inference algorithms which use a model to make predictions about data. Understanding the intricacies of these interactions is crucial for advancing the state-of-the-art on real-world tasks in natural language processing, computer vision, computation biology, etc. Yet, many facets of these interactions remain unknown. In this workshop, we study the interactions between inference and learning using two reciprocating perspectives. Perspective one: how does inference affect learning? The first perspective studies the influence of the choice of inference technique during learning on the resulting model. When faced with models for which exact inference is intractable, efficient approximate inference techniques may be used, such as MCMC sampling, stochastic approximation, belief propagation, beam-search, dual decomposition, etc. The workshop will focus on work that evaluates the impact of the approximations on the resulting parameters, in terms of both the generalization of the model, the effect it has on the objective functions, and the convergence properties. We will also study approaches that attempt to correct for the approximations in inference by modifying the objective and/or the learning algorithm (for example, contrastive divergence for deep architectures), and approaches that minimize the dependence on the inference algorithms by exploring inference-free methods (e.g., piece-wise training, pseudo-max and decomposed learning). Perspective two: how does learning affect inference? Traditionally, the goal of learning has been to find a model for which prediction (i.e., inference) accuracy is as high as possible. However, an increasing emphasis on modeling complexity has shifted the goal of learning: find models for which prediction (i.e., inference) is as efficient as possible. Thus, there has been recent interest in more unconventional approaches to learning that combine generalization accuracy with other desiderata such as faster inference. Some examples of this kind are: learning classifiers for greedy inference (e.g., Searn, Dagger); structured cascade models that learn a cost function to perform multiple runs of inference from coarse to fine level of abstraction by trading-off accuracy and efficiency at each level; learning cost function to search in the space of complete outputs (e.g., SampleRank, search in Limited Discrepancy Search space); learning structures that exhibit efficient exact inference etc. Similarly, there has been work that learns operators for efficient search-based inference, approaches that trade-off speed and accuracy by incorporating resource constraints such as run-time and memory into the learning objective.

List of Topics

This workshop brings together practitioners from different fields (information extraction, machine vision, natural language processing, computational biology, etc.) in order to study a unified framework for understanding and formalizing the interactions between learning and inference. The following is a partial list of relevant keywords for the workshop:

learning with approximate inference

cost-aware learning

learning sparse structures

pseudo-likelihood, composite likelihood training

contrastive divergence

piece-wise and decomposed training

decomposed learning

coarse to fine learning and inference

scoring matching

stochastic approximation

incremental gradient methods

adaptive proposal distributions

learning for anytime inference

learning approaches that trade-off speed and accuracy

learning to speed up inference

learning structures that exhibit efficient exact inference

lifted inference for first-order models

more …

New benchmark problems: This line of research can hugely benefit from new challenge problems from various fields (e.g., computer vision, natural language processing, speech, computational biology, computational sustainability etc.). Therefore, we especially request relevant papers describing such problems, main challenges, evaluations and public data sets.

Invited Speakers

Dan Roth, University of Illinois, Urbana-Champaign

Rina Dechter, University of California, Irvine

Ben Taskar, University of Washington

Hal Daume, University of Maryland, College Park

Alan Fern, Oregon State University

Important Dates

Submission Deadline: April 20th, 2013 (11:59pm PST)Author Notification: May 13th, 2013Workshop: June 20-21, 2013
Author Guidelines

Submissions are encouraged as extended abstracts of ongoing research. The recommended page length is 4-6 pages. Additional supplementary content may be included, but may not be considered during the review process. Previously published or currently in submission papers are also encouraged (we will confirm with authors before publishing the papers online).The format of the submissions should follow the ICML 2013 style, available here: http://icml.cc/2013/wp-content/uploads/2012/12/icml2013stylefiles.tar.gz. However, since the review process is not double-blind, submissions need not be anonymized and author names may be included.

Open Review

Our workshop will be following the open reviewing system as introduced by the International Conference on Learning Representations (ICLR). In particular, the submitted papers will be available for public comment after the submission deadline. Along with the public comments, we will also provide anonymous reviews by our program committee members. The decisions for acceptance will be based on a combination of review scores and insights from the public discourse. If you have any concerns or questions regarding the reviewing process, please email us atinferning2013@gmail.com. 

Submission site: http://openreview.net/inferning2013

Organizers

Janardhan Rao (Jana) Doppa, Oregon State University

Pawan Kumar, Ecole Centrale Paris

Michael Wick, University of Massachusetts, Amherst

Sameer Singh, University of Massachusetts, Amherst

Ruslan Salakhutdinov, University of Toronto

On Thu, Mar 28, 2013 at 1:04 PM, Ruslan Salakhutdinov wrote:

Sure,
let me know once the website is done with modified dates for paper
submission. I will post CFP to various ML lists.
Russ

On 3/28/13 12:07 PM, Janardhan Rao (Jana) Doppa wrote:

Once Sameer is done updating the website, Rus and you
can copy the CFP and send it to the appropriate mailing lists.
Thanks,
Jana
On Thu, Mar 28, 2013 at 9:04 AM, Pawan
wrote:

Please send me the updated CFP as well. I’ll
post it on the vision mailing lists.

On Thu, Mar 28, 2013 at 4:48
PM, Michael Wick
wrote:

Our openreview.net
page is up. It’s just a stub right now. David is
estimating April 10th as the day it will be open
for submission. http://openreview.net/inferning2013

On 3/27/13 7:10 PM, Ruslan Salakhutdinov
wrote:

Let me know what you guys want to put into
our second CFP, and I can send it out
tomorrow evening.
Russ
On 3/27/13 6:26 PM, Sameer Singh wrote:

We’ll try to have the info
regarding OpenReview by tomm, but yes,
we should send out the CFP in any case
by tomm night.

On Wed, Mar 27,
2013 at 6:16 PM, Janardhan Rao (Jana)
Doppa
wrote:
We need to a
send a new CFP soon (preferably
tomorrow or Friday) so that authors’
can plan accordingly — we said Mar
30 in the previous CFP!
We can send the OpenReview
information later also (another
call) once we know all the details.
What do you think ?

On Wed,
Mar 27, 2013 at 3:10 PM,
Sameer Singh
wrote:

Note that the
biggest change from our
side will be moving the
whole setup away from
EasyChair (leaving it
entirely), and committing
to using the OpenReview
system. This includes
using it for submission of
papers, creating a PC,
assigning papers to the
reviewers, and submitting
the reviews.

For submitting the
papers, it needs to be
ready definitely before
April 20, but preferably
a few weeks before that
so authors can submit
the papers somewhere.
Mike and I can find out
the exact date very
soon.

On
Wed, Mar 27, 2013 at
6:05 PM, Janardhan
Rao (Jana) Doppa
wrote:
Thanks

Mike. Do we plan
to handle our
submissions
through open
review ? In that
case, it should be
ready by April 20
(our paper
submission
deadline).

On
Wed, Mar 27,
2013 at 2:58
PM, Michael
Wick
wrote:

Hi
Jana,
I spoke
briefly with
David Soergel
about
OpenReview.net.
He’ll set up a
URL for us in
the next day
or
s


[Imageworld] Research Internship at Mitsubishi Electric Research Laboratories (MERL)

Job Description:  MERL’s Imaging group is
seeking a highly motivated intern to work on scene understanding
and depth estimation algorithms. The ideal candidate would be in
the middle or second half of a Ph.D. program in computer vision or
robotics, and have background in segmentation, motion and depth
estimation from stereo cameras. Strong programming skill in C++ is
expected. Hands-on hardware experience and GPU programming are a
plus. The duration of the internship will be from 3 to 6 months.

Position ID: IM693Contact:  Srikumar
RamalingamEmail: