[visionlist] [Call for participants]: 2nd Unconstrained Ear Recognition Challenge (UERC 2019)

[Vitomir Štruc]

********************************************************
CALL FOR PARTICIPANTS

2nd Unconstrained Ear Recognition Challenge (UERC 2019)
Organized as part of IAPR ICB 2019
REGISTRATION IS OPEN

http://ears.fri.uni-lj.si/uerc19
********************************************************

** CALL FOR PARTICIPANTS **
We invite researchers working in the field of automatic ear recognition 
(in the wild to participate in the 2nd
Unconstrained Ear Recognition Challenge (UERC 2019) that will be held in 
the scope of the IAPR
International Conference on Biometrics (ICB 2019). The goal of the 
challenge is to advance the
state-of-technology in the field of automatic ear recognition, to 
provide participants with a challenging
research problem and introduce a benchmark dataset and protocol for 
assessing the latest techniques,
models, and algorithms related to ear recognition. If you are interested 
in taking part in UERC, please visit:


http://ears.fri.uni-lj.si/uerc19

** Data **
The challenge will be held on the extended version of the Annotated Web 
Ears (AWEx) dataset.
Images of the dataset were collected with a semi-automatic procedure 
that involved web-crawlers and
a manual inspection. Because the AWEx images were not gathered in 
laboratory-like conditions, they better
represent the variability in ear appearance than existing datasets of 
ear images. Images of the AWEx dataset
contain various annotations, such as the level of occlusion, rotation 
(yaw, roll, and pitch angles), presence
of accessories, gender and side. This information is also made available 
to the participants and can be used
to build specialized recognition techniques. An additional dataset with 
over 3300 identities will be used to
test the scalability of the submitted algorithms.

** Setup **
UERC 2019 will test the recognition performance of all submitted 
algorithms through identification
experiments. The participants will have to submit similarity matrices of 
their algorithms, which will then
be scored by the organizers. Rank-1 recognition rates, CMC curves and 
the Area-Under-the CMC Curve
(AUC) will be computed and reported for all submitted algorithms. The 
three top performing algorithms
will be independently evaluated by the organizers on some sequestered data.

** Publication **
The results of UERC 2019 will be published in an ICB 2019 conference 
paper co-authored
jointly by all challenge participants contributing an algorithm (with 
some original aspect) to the challenge.

** Organizers **
Ziga Emersic
Hazim Kemal Ekenel
Li Yuan
Peter Peer
Vitomir Struc

** Important Dates **
Registration is open!

Registration ends:     15 December, 2018
Results due:          15 January, 2019
Descriptions due:     15 January, 2019
Joint-paper submission:     11 February, 2019

-- 
Assoc. Prof. Vitomir Štruc, PhD
Laboratory for Machine Intelligence
Faculty of Electrical Engineering
University of Ljubljana
Slovenia
Tel: +386 1 4768 839
Fax: +386 1 4768 316
URL: luks.fe.uni-lj.si/nluks/people/vitomir-struc/


Finance Chair: Automatic Face and Gesture Recognition 2019

Guest editor: Image and Vision Computing SI: Biometrics in the Wild