<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=us-ascii">
<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;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
        {margin:0cm;
        font-size:11.0pt;
        font-family:"Calibri",sans-serif;
        mso-fareast-language:EN-US;}
a:link, span.MsoHyperlink
        {mso-style-priority:99;
        color:#0563C1;
        text-decoration:underline;}
span.EmailStyle17
        {mso-style-type:personal-compose;
        font-family:"Calibri",sans-serif;
        color:windowtext;}
.MsoChpDefault
        {mso-style-type:export-only;
        font-family:"Calibri",sans-serif;
        mso-fareast-language:EN-US;}
@page WordSection1
        {size:612.0pt 792.0pt;
        margin:72.0pt 72.0pt 72.0pt 72.0pt;}
div.WordSection1
        {page:WordSection1;}
--></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="EN-CA" link="#0563C1" vlink="#954F72" style="word-wrap:break-word">
<div class="WordSection1">
<p align="center" style="margin:0cm;text-align:center;background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">[Apologies for cross-postings / Please send to interested colleagues]</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p align="center" style="margin:0cm;text-align:center;background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">Call for Papers</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p align="center" style="margin:0cm;text-align:center;background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">CVPR 2023 Workshop</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p align="center" style="margin:0cm;text-align:center;background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">DL-UIA: Deep Learning in Ultrasound Image Analysis</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p align="center" style="margin:0cm;text-align:center;background:white"><b><span style="font-family:"Arial",sans-serif;color:#444444;background:white"><a href="https://www.cvpr2023-dl-ultrasound.com/">https://www.cvpr2023-dl-ultrasound.com/</a></span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p align="center" style="margin:0cm;text-align:center;background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">June 18<sup>th</sup>, 2023, Vancouver, Canada</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p align="center" style="margin:0cm;text-align:center;background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">Deadline for submissions:
</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p align="center" style="margin:0cm;text-align:center;background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">March 3<sup>rd</sup>, 2023</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p align="center" style="margin:0cm;text-align:center;background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">Challenge opens soon!</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p style="margin:0cm;background:white"><b><span style="font-family:"Arial",sans-serif;color:#444444;background:white"><o:p> </o:p></span></b></p>
<p style="margin:0cm;background:white"><b><span style="font-family:"Arial",sans-serif;color:#444444;background:white"><o:p> </o:p></span></b></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">Dear fellow researchers,</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">You are cordially invited to attend the Deep Learning in Ultrasound Image Analysis Workshop (DL-UIA), to be held in conjunction with CVPR 2023 on June 18<sup>th</sup>,
 in Vancouver, Canada. </span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">Ultrasound (US) has become one of the most common imaging modalities in the past two decades in fields such as sonar, non-destructive testing (NDT), and biomedical
 imaging. NDT is used to evaluate material integrity in many scenarios, such as jet engines in aerospace, and critical infrastructure and assets in natural resource transportation and energy production. Solving computer vision/image analysis problems in NDT,
 such as defect/flaw identification, crack detection, and defect characterization in a timely and accurate manner not only could help save billions of dollars worldwide annually but could also bring tremendous social impact regarding applications such as aircraft
 condition monitoring, concrete inspection, and rail condition monitoring.</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">Computer vision techniques in NDT have advanced during the past years. Modern NDT ultrasound machines can easily collect vast quantities of high-resolution
 images in a short amount of time. In one example, a 360-degree view, a full circumferential scan of thousands of meters of pipe can be imaged at sub-millimetric resolution in a single continuous pass. This not only makes the existing computer vision tasks
 in NDT challenging, such as data pre-processing, defect detection, defect characterization, and property measurement, but also introduces unique challenges regarding deep learning, such as extreme data imbalance, multi-task learning, weakly supervised learning,
 and semi-supervised learning problems. Moreover, due to the special modality of ultrasound, there are still gaps between natural images-derived deep learning algorithms and ultrasound images-based deep learning algorithms, such as focused image denoising,
 image interpretation, uncertainty quantification, and automated system self-awareness.</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">Topics of Interests</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">In the DL-UIA: Deep Learning in Ultrasound Image Analysis Workshop, we welcome papers on a wide variety of topics, including but not limited to:</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Computer Vision in Ultrasound Images</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Algorithms to Mitigate Data Imbalance</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Semi-supervised Learning in Ultrasound Images</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Weakly-supervised Learning in Ultrasound Images</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Supervised Learning in Ultrasound Images</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Multi-task Learning in Ultrasound Images</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Deep Learning in Volumetric Images</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Data and Performance Baseline</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Normalization Techniques in Ultrasound Image Analysis</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Image Classification and Segmentation</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Spatial-temporal Feature Analysis</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">Paper Submission</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">Each paper submission will be double-blind peer-reviewed and should be limited to eight pages, including figures and tables, following the same policies and
 submission guidelines described in CVPR'23 Author Guidelines (<a href="https://cvpr2023.thecvf.com/Conferences/2023/AuthorGuidelines">https://cvpr2023.thecvf.com/Conferences/2023/AuthorGuidelines</a> ). Selected papers will be presented as either oral or poster
 presentations and will appear in the CVPR conference proceedings. Papers submission is done through the CMT system. When submitting a manuscript to this workshop, the authors acknowledge that no paper with substantially similar content has been submitted to
 another workshop or conference during the review period.</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">Challenge Submission</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">Together with the workshop, we are releasing (open soon) an open 3D industrial ultrasound image dataset for the 3D surface mesh estimation challenge. Individuals
 or teams are welcome to register and submit to the competition. Please visit our website for more information:
<a href="https://www.cvpr2023-dl-ultrasound.com/">https://www.cvpr2023-dl-ultrasound.com/</a>
</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><b><span style="font-family:"Arial",sans-serif;color:black;background:white">Key Dates</span></b><b><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></b></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Workshop paper submission deadline: March 3<sup>rd</sup>, 2023</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Notification of acceptance: April 3<sup>rd</sup>, 2023</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p style="margin:0cm;background:white"><span style="font-family:"Arial",sans-serif;color:black;background:white">•           Camera-ready submission: April 8<sup>th</sup>, 2023</span><span style="font-family:"Arial",sans-serif;background:white"><o:p></o:p></span></p>
<p align="center" style="margin:0cm;text-align:center;background:white"><span style="font-size:12.0pt;font-family:"Arial",sans-serif;color:#222222;background:white"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="font-family:"Arial",sans-serif">Organizers<o:p></o:p></span></b></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif">Mengliu Zhao, DarkVision Technologies<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif">Mike Wong, DarkVision Technologies<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif">Amirmasoud Ghasemi, DarkVision Technologies<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif">Carlos Alberto da Costa Filho, DarkVision Technologies<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif">Gaurav Handa, DarkVision Technologies<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif">Zahra Mirikharaji, DarkVision Technologies<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif">Jason Vantomme, DarkVision Technologies<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif">Reza Zahiri, DarkVision Technologies<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif"><a href="mailto:cvpr2023.dl.ultrasound@gmail.com">cvpr2023.dl.ultrasound@gmail.com</a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif"><a href="https://www.cvpr2023-dl-ultrasound.com">https://www.cvpr2023-dl-ultrasound.com</a>
<o:p></o:p></span></p>
</div>
</body>
</html>