<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=utf-8"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:"Calibri Light";
panose-1:2 15 3 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
h1
{mso-style-priority:9;
mso-style-link:"Επικεφαλίδα 1 Char";
mso-margin-top-alt:auto;
margin-right:0in;
mso-margin-bottom-alt:auto;
margin-left:0in;
font-size:24.0pt;
font-family:"Calibri",sans-serif;
font-weight:bold;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
span.1Char
{mso-style-name:"Επικεφαλίδα 1 Char";
mso-style-priority:9;
mso-style-link:"Επικεφαλίδα 1";
font-family:"Calibri Light",sans-serif;
color:#2F5496;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
mso-ligatures:none;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.25in 1.0in 1.25in;}
div.WordSection1
{page:WordSection1;}
/* List Definitions */
@list l0
{mso-list-id:53740000;
mso-list-template-ids:1206685126;}
@list l1
{mso-list-id:483857984;
mso-list-template-ids:-1466012998;}
@list l1:level1
{mso-level-tab-stop:.5in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l1:level2
{mso-level-tab-stop:1.0in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l1:level3
{mso-level-tab-stop:1.5in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l1:level4
{mso-level-tab-stop:2.0in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l1:level5
{mso-level-tab-stop:2.5in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l1:level6
{mso-level-tab-stop:3.0in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l1:level7
{mso-level-tab-stop:3.5in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l1:level8
{mso-level-tab-stop:4.0in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l1:level9
{mso-level-tab-stop:4.5in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l2
{mso-list-id:1054933457;
mso-list-template-ids:-1706921206;}
@list l3
{mso-list-id:2047217194;
mso-list-template-ids:650034946;}
@list l3:level1
{mso-level-tab-stop:.5in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l3:level2
{mso-level-tab-stop:1.0in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l3:level3
{mso-level-tab-stop:1.5in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l3:level4
{mso-level-tab-stop:2.0in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l3:level5
{mso-level-tab-stop:2.5in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l3:level6
{mso-level-tab-stop:3.0in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l3:level7
{mso-level-tab-stop:3.5in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l3:level8
{mso-level-tab-stop:4.0in;
mso-level-number-position:left;
text-indent:-.25in;}
@list l3:level9
{mso-level-tab-stop:4.5in;
mso-level-number-position:left;
text-indent:-.25in;}
ol
{margin-bottom:0in;}
ul
{margin-bottom:0in;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=EL link=blue vlink=purple style='word-wrap:break-word'><div class=WordSection1><p class=MsoNormal style='margin-bottom:12.0pt'><span lang=EN-US>Dear Machine Learning, Computer Vision and Autonomous Systems engineers, scientists and enthusiasts,</span><span lang=EN-US style='font-size:10.5pt'><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'>you are welcomed to register in the <strong><span style='font-family:"Calibri",sans-serif'>CVML Short course on Deep Learning and Computer Vision, 28-29<sup>th</sup> August 2023:</span></strong><br></span><u><span style='font-size:10.5pt'><a href="https://icarus.csd.auth.gr/cvml-short-course-deep-learning-and-computer-vision-2023/" target=6r4WMzaxi6hEkjLyyyYkPVE><span lang=EN-US>https://icarus.csd.auth.gr/cvml-short-course-deep-learning-and-computer-vision-2023/</span></a></span></u><span lang=EN-US style='font-size:10.5pt'> <br>with various Computer Vision and Deep Learning applications, e.g., for big visual data analysis, autonomous vehicles (drones, cars and marine vessels), digital media analysis, intelligent human-machine interaction, anthropocentric (human-centered) computing, smart cities/buildings and assisted living, natural disaster management. <o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'><br>It will take place at <a href="https://www.google.com/maps/place/Aristotle+University+Research+Dissemination+Center+(KEDEA)/@40.6268129,22.9625765,15z/data=!4m2!3m1!1s0x0:0xd56ca8d4f0abc5de?sa=X&ved=2ahUKEwjxk_zdz6H_AhXG_aQKHReeDFkQ_BJ6BAhJEAg">KEDEA</a> Building, hosted by the Aristotle University of Thessaloniki (AUTH), Thessaloniki, Greece.<br>The course consists of 16 lectures, providing an in-depth presentation of many computer vision and deep learning hot topics, finding applications in big visual data analysis, autonomous vehicle vision, digital media analysis and human centered computing. There will be complemented with lecture pdfs to enable you to study at own pace. <o:p></o:p></span></p><p><span lang=EN-US style='font-size:10.5pt'>You can also self-assess your knowledge, by filling appropriate questionnaires (one per lecture).<br>You will be provided programming pointers to improve your skills.<br>You will also have access to tutorial exercises to better your theoretical understanding of selected CVML topics.<br>This 6<sup>th</sup> edtion of this course is part of the very successful CVML short course series that has been taking place in the last four years.<o:p></o:p></span></p><h1 style='margin:0in'><span lang=EN-US style='font-size:12.0pt'>Course description ‘Deep Learning and Computer Vision’<o:p></o:p></span></h1><p style='margin:0in'><span lang=EN-US style='font-size:10.5pt'> <o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'>The short course consists of <strong><span style='font-family:"Calibri",sans-serif'>16 live lectures</span></strong> organized in two Parts (1 Part per day):<br><strong><span style='font-family:"Calibri",sans-serif'>Part A lectures (8 hours)</span></strong> provide an in-depth presentation of Deep Neural Networks, which are at the forefront of AI advances today, starting with an introduction to Machine Learning. Then the cornerstone DNN theory and technologies are presented.<br><strong><span style='font-family:"Calibri",sans-serif'>Part B lectures (8 hours)</span></strong> provide an in-depth presentation of both 2D and 3D Computer Vision theory and its applications in the above-mentioned diverse domains. 3D Computer Vision starts with a detailed presentation of camera geometry, including camera calibration.<br> <br> <br></span><strong><span style='font-size:10.5pt;font-family:"Calibri",sans-serif'>Course lectures</span></strong><span style='font-size:10.5pt'><br><strong><span style='font-family:"Calibri",sans-serif'>Part A (8 hours), Deep Neural Networks topic list</span></strong><o:p></o:p></span></p><p style='margin:0in'><span style='font-size:10.5pt'> <o:p></o:p></span></p><ol style='margin-top:0in' start=1 type=1><li class=MsoNormal style='mso-list:l1 level1 lfo3'><span style='font-size:10.5pt'>Multilayer perceptron. Backpropagation <o:p></o:p></span></li><li class=MsoNormal style='mso-list:l1 level1 lfo3'><span lang=EN-US style='font-size:10.5pt'>Deep neural networks. Convolutional NNs <o:p></o:p></span></li><li class=MsoNormal style='mso-list:l1 level1 lfo3'><span style='font-size:10.5pt'>Recurrent Neural Networks <o:p></o:p></span></li><li class=MsoNormal style='mso-list:l1 level1 lfo3'><span style='font-size:10.5pt'>Attention and Transformers</span><o:p></o:p></li><li class=MsoNormal style='mso-list:l1 level1 lfo3'><span style='font-size:10.5pt'>Attention in Computer Vision<o:p></o:p></span></li><li class=MsoNormal style='mso-list:l1 level1 lfo3'><span style='font-size:10.5pt'>Generative Adversarial Networks <o:p></o:p></span></li><li class=MsoNormal style='mso-list:l1 level1 lfo3'><span style='font-size:10.5pt'>Diffusion Models <o:p></o:p></span></li><li class=MsoNormal style='mso-list:l1 level1 lfo3'><span style='font-size:10.5pt'>Deep Reinforcement Learning models <o:p></o:p></span></li></ol><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'> <br><strong><span style='font-family:"Calibri",sans-serif'>Part B (8 hours) 2D and 3D Computer Vision topic list</span></strong><o:p></o:p></span></p><p style='margin:0in'><span lang=EN-US style='font-size:10.5pt'> <o:p></o:p></span></p><ol style='margin-top:0in' start=1 type=1><li class=MsoNormal style='mso-list:l3 level1 lfo6'><span style='font-size:10.5pt'>Camera geometry <o:p></o:p></span></li><li class=MsoNormal style='mso-list:l3 level1 lfo6'><span style='font-size:10.5pt'>Stereo and Multiview imaging <o:p></o:p></span></li><li class=MsoNormal style='mso-list:l3 level1 lfo6'><span style='font-size:10.5pt'>Structure from motion <o:p></o:p></span></li><li class=MsoNormal style='mso-list:l3 level1 lfo6'><span style='font-size:10.5pt'>Object detection and tracking <o:p></o:p></span></li><li class=MsoNormal style='mso-list:l3 level1 lfo6'><span lang=EN-US style='font-size:10.5pt'>Region segmentation and pose estimation <o:p></o:p></span></li><li class=MsoNormal style='mso-list:l3 level1 lfo6'><span style='font-size:10.5pt'>Human action recognition <o:p></o:p></span></li></ol><p style='mso-margin-top-alt:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in'><span style='font-size:10.5pt'> <o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'> <br>Though independent, the attendees of this short course will greatly benefit by attending the CVML Programming Short Course and Workshop on Deep Learning and Computer Vision 2022, that will take place between August 30 and September 1, 2023:<br></span><span style='font-size:10.5pt'><a href="http://icarus.csd.auth.gr/cvml-programming-short-course-and-workshop-on-deep-learning-and-computer-vision-2023/"><span lang=EN-US>http://icarus.csd.auth.gr/cvml-programming-short-course-and-workshop-on-deep-learning-and-computer-vision-2023/</span></a></span><span lang=EN-US style='font-size:10.5pt'><br> <br><strong><span style='font-family:"Calibri",sans-serif'>You can use the following link for course registration:</span></strong><br><a href="https://rc.auth.gr/product-list/single-product/125">https://rc.auth.gr/product-list/single-product/125</a><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'><o:p> </o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'>For questions, please contact: Ioanna Koroni <</span><span style='font-size:10.5pt'><a href="mailto:koroniioanna@csd.auth.gr"><span lang=EN-US>koroniioanna@csd.auth.gr</span></a></span><span lang=EN-US style='font-size:10.5pt'>><br> <br>The short course is organized by Prof. I. Pitas, IEEE and EURASIP fellow and IEEE distinguished speaker. He is the coordinator of the EC funded International AI Doctoral Academy (</span><span style='font-size:10.5pt'><a href="http://www.i-aida.org/" target="oSd7msqJ_d4r-6QSHtkY9-J"><span lang=EN-US>AIDA</span></a></span><span lang=EN-US style='font-size:10.5pt'>), that is co-sponsored by all 5 European AI R&D flagship projects (H2020 ICT48). He was initiator and first Chair of the IEEE SPS Autonomous Systems Initiative. He is Director of the Artificial Intelligence and Information analysis Lab (AIIA Lab), Aristotle University of Thessaloniki, Greece. He is Coordinator of the European Horizon2022 R&D project TEMA and he was Coordinator of the European Horizon2020 R&D project Multidrone. He is ranked 249-top Computer Science and Electronics scientist internationally by Guide2research (2018). He has 35500+ citations to his work and h-index 86+.<br> <br>AUTH is ranked 153/182 internationally in Computer Science/Engineering, respectively, in USNews ranking.<br> <br>Relevant links:<br>1) Prof. I. Pitas: </span><span style='font-size:10.5pt'><a href="https://scholar.google.gr/citations?user=lWmGADwAAAAJ&hl=el" target="QvJuhGQ_lqhKhAA71OKKzMj"><span lang=EN-US>https://scholar.google.gr/citations?user=lWmGADwAAAAJ&hl=el</span></a></span><span lang=EN-US style='font-size:10.5pt'><br>2) Horizon2022 EU funded R&D project TEMA: <a href="https://tema-project.eu/">https://tema-project.eu/</a><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'>3) Horizon2022 EU funded R&D project AI4EUROPE: <a href="https://www.ai4europe.eu/">https://www.ai4europe.eu/</a><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'>4) Horizon2020 EU funded R&D project Aerial-Core: </span><span style='font-size:10.5pt'><a href="https://aerial-core.eu/" target=73fiG72bY2jQ-zD9Y6EjQEn><span lang=EN-US>https://aerial-core.eu/</span></a></span><span lang=EN-US><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'>5) Horizon2020 EU funded R&D project Multidrone: </span><span style='font-size:10.5pt'><a href="https://multidrone.eu/" target="4nt7IgjMkWDF_bDlCZdJ7vY"><span lang=EN-US>https://multidrone.eu/</span></a></span><span lang=EN-US style='font-size:10.5pt'><br>6) International AI Doctoral Academy (AIDA): </span><span style='font-size:10.5pt'><a href="http://www.i-aida.org/" target=liPJhETvqqtxSf1DGRT1HbA><span lang=EN-US>http://www.i-aida.org/</span></a></span><span lang=EN-US style='font-size:10.5pt'><br>7) Horizon2020 EU funded R&D project AI4Media: </span><span style='font-size:10.5pt'><a href="https://ai4media.eu/" target="CU_xtSvi35ck1yKtoXY7peQ"><span lang=EN-US>https://ai4media.eu/</span></a></span><span lang=EN-US style='font-size:10.5pt'><br>8) AIIA Lab: </span><span style='font-size:10.5pt'><a href="https://aiia.csd.auth.gr/" target=ZMfgYBt77sjJ-vYo6PoYjgp><span lang=EN-US>https://aiia.csd.auth.gr/</span></a></span><span lang=EN-US style='font-size:10.5pt'><br> <br>Sincerely yours<br>Prof. I. Pitas<br>Director of the Artificial Intelligence and Information analysis Lab (AIIA Lab)<br>Chair of the International AI Doctoral Academy (AIDA)<br>Aristotle University of Thessaloniki, Greece<br> <br>Post scriptum: To stay current on CVML matters, you may want to register in the CVML email list, following instructions in: </span><span style='font-size:10.5pt'><a href="https://lists.auth.gr/sympa/info/cvml" target=FuItl94UoFQJvHFSncmyvGC><span lang=EN-US>https://lists.auth.gr/sympa/info/cvml</span></a></span><span lang=EN-US><o:p></o:p></span></p><p class=MsoNormal><span lang=EN-US style='font-size:10.5pt'><o:p> </o:p></span></p></div></body></html>