ECCV 2022 Sign Spotting Challenge Call for Papers
We cordially invite you to participate in our
ECCV 2022 Sign Spotting Challenge
Challenge description: To advance and motivate the research on Sign
Language Recognition (SLR), the challenge will use a partially
annotated continuous sign language dataset of more than 10 hours of
video data in the health domain and will address the challenging
problem of fine-grain sign spotting in continuous SLR. In this
context, we want to put a spotlight on the strengths and limitations
of the existing approaches, and define the future directions of the
field. It will be divided in two competition tracks:
Multiple Shot Supervised Learning (MSSL) is a classical machine
learning Track where signs to be spotted are the same in training,
validation and test sets. The three sets will contain samples of
signs cropped from the continuous stream of Spanish sign language,
meaning that all of them have co-articulation influence. The
training set contains the begin-end timestamps annotated by a deaf
person and a SL-interpreter with a homogeneous criterion of
multiple instances for each of the query signs. Participants will
need to spot those signs in a set of validation videos with
captured annotations. The signers in the test set can be the same
or different to the training and validation set. Signers are men,
women, right and left-handed.
One Shot Learning and Weak Labels (OSLWL) is a realistic variation
of a one-shot learning problem adapted to the sign language
specific problem, where it is relatively easy to obtain a couple
of examples of a sign, using just a sign language dictionary, but
it is much more difficult to find co-articulated versions of that
specific sign. When subtitles are available, as in broadcast-based
datasets, the typical approach consists of using the text to
predict a likely interval where the sign might be performed. So in
this track we simulate that case by providing a set of queries
(isolated signs) and a set of video intervals around each and
every co-articulated instance of the queries. Intervals with no
instances of queries are also provided as negative
groundtruth. Participants will need to spot the exact location of
the sign instances in the provided video intervals.
Challenge webpage: http://chalearnlap.cvc.uab.es/challenge/45/description/
Tentative Schedule:
Start of the Challenge (development phase): April 20, 2022
Start of test phase: June 17, 2022
End of the Challenge: June 24, 2022
Release of final results: July 1st, 2022
Participants are invited to submit their contributions to the
associated ECCV'22 Workshop
(https://chalearnlap.cvc.uab.cat/workshop/50/description/),
independently of their rank position.
ORGANIZATION and CONTACT
Sergio Escalera ,
Computer Vision Center (CVC) and University of Barcelona, Spain
Jose L. Alba-Castro , atlanTTic
research center, University of Vigo, Spain
Thomas B. Moeslund, Aalborg University, Aalborg, Denmark
Julio C. S. Jacques Junior, Computer Vision Center (CVC), Spain
Manuel Vázquez Enri´quez, atlanTTic research center,
University of Vigo, Spain