<div dir="ltr">
<p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt" id="gmail-docs-internal-guid-de1b6efd-7fff-208c-31b3-ccc783b3ee2d"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">We cordially invite you to participate in our </span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-style:italic;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">ECCV’2022 Sign Spotting Challenge </span></p><br><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:6pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Challenge description:</span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"> 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:</span></p><ol style="margin-top:0px;margin-bottom:0px"><li dir="ltr" style="list-style-type:decimal;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Multiple Shot Supervised Learning (MSSL) </span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">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.</span></p></li></ol><br><ol style="margin-top:0px;margin-bottom:0px" start="2"><li dir="ltr" style="list-style-type:decimal;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">One Shot Learning and Weak Labels (OSLWL)</span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"> 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. </span></p></li></ol><br><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:6pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Challenge webpage: </span><a href="https://chalearnlap.cvc.uab.cat/challenge/49/description/" style="text-decoration:none"><span style="font-size:10pt;font-family:Arial;color:rgb(17,85,204);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;vertical-align:baseline;white-space:pre-wrap">https://chalearnlap.cvc.uab.cat/challenge/49/description/</span></a><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"> </span></p><br><p dir="ltr" style="line-height:1.38;margin-left:36pt;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;vertical-align:baseline;white-space:pre-wrap">Tentative Schedule:</span></p><br><ul style="margin-top:0px;margin-bottom:0px"><li dir="ltr" style="list-style-type:disc;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;margin-left:36pt"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Start of the Challenge (development phase): </span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">April 20, 2022</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;margin-left:36pt"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Start of test phase: </span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">June 17, 2022</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;margin-left:36pt"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">End of the Challenge: </span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">June 24, 2022</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre;margin-left:36pt"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Release of final results: </span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">July 1st, 2022</span></p></li></ul><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Participants are invited to submit their contributions to the associated ECCV’22 Workshop (</span><a href="https://chalearnlap.cvc.uab.cat/workshop/50/description/" style="text-decoration:none"><span style="font-size:10pt;font-family:Arial;color:rgb(17,85,204);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;vertical-align:baseline;white-space:pre-wrap">https://chalearnlap.cvc.uab.cat/workshop/50/description/</span></a><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">), independently of their rank position.</span></p><br><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:underline;vertical-align:baseline;white-space:pre-wrap">ORGANIZATION and CONTACT</span></p><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Sergio Escalera </span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"><</span><a href="mailto:sergio.escalera.guerrero@gmail.com" style="text-decoration:none"><span style="font-size:10pt;font-family:Arial;color:rgb(17,85,204);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;vertical-align:baseline;white-space:pre-wrap">sergio.escalera.guerrero@gmail.com</span></a><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">>, Computer Vision Center (CVC) and University of Barcelona, Spain</span></p><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Jose L. Alba-Castro</span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap"> <</span><a href="mailto:jalba@gts.uvigo.es" style="text-decoration:none"><span style="font-size:10pt;font-family:Arial;color:rgb(17,85,204);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:underline;vertical-align:baseline;white-space:pre-wrap">jalba@gts.uvigo.es</span></a><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">>, atlanTTic research center, University of Vigo, Spain</span></p><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Thomas B. Moeslund</span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">, Aalborg University, Aalborg, Denmark</span></p><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Julio C. S. Jacques Junior</span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">, Computer Vision Center (CVC), Spain</span></p><p dir="ltr" style="line-height:1.38;text-align:justify;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:700;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">Manuel Vázquez Enrı́quez</span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:rgb(255,255,255);font-weight:400;font-style:normal;font-variant:normal;text-decoration:none;vertical-align:baseline;white-space:pre-wrap">, atlanTTic research center, University of Vigo, Spain</span></p>

<br clear="all"><br>-- <br><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div><font size="1"><span style="color:rgb(68,68,68)"><b><span style="color:rgb(102,102,102)">Dr. Sergio Escalera Guerrero</span></b></span><span style="color:rgb(153,153,153)"></span></font><div><span style="color:rgb(153,153,153)"><font size="1"><span><span><span style="color:rgb(153,153,153)"><font size="1">Full Professor</font></span></span></span> at Universitat de Barcelona</font></span></div><font size="1"><span style="color:rgb(153,153,153)"><font size="1"><span style="color:rgb(153,153,153)">ELLIS Fellow / </span></font>Head of Human Pose Recovery and Behavior Analysis group /</span></font><span style="color:rgb(153,153,153)"><font size="1"> ICREA Academia / Project Manager at the Computer Vision Center</font></span><span style="color:rgb(153,153,153)"></span><br><span style="color:rgb(153,153,153)"></span></div></div><font size="1"><span style="color:rgb(153,153,153)">Email: <a href="mailto:sergio.escalera.guerrero@gmail.com" target="_blank">sergio.escalera.guerrero@gmail.com</a> / Webpage: <a href="http://www.maia.ub.es/~sergio/" target="_blank">http://www.sergioescalera.com/</a></span></font><span><span style="color:rgb(153,153,153)"><font size="1">  / Phone:+34</font></span><font size="1"><span style="color:rgb(153,153,153)"><font size="1"><span dir="ltr"><span dir="ltr"><span><span>934020853<br></span></span></span></span></font></span></font></span><div><span></span></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div>