[visionlist] CFP - CVPR 2023 Workshop on Deep Learning in Ultrasound Image Analysis (Deadline Extended)

[Zhao, Mengliu]

[Apologies for cross-postings / Please send to interested colleagues]
Call for Papers
CVPR 2023 Workshop
DL-UIA: Deep Learning in Ultrasound Image Analysis
https://www.cvpr2023-dl-ultrasound.com/<https://urldefense.com/v3/__https:/www.cvpr2023-dl-ultrasound.com/__;!!HKYIif90!xiX85HNGHmYboTJ_tMNi9_yfa2m5OB7gsaPjK7MrqymYZiJkvnZ-59sLJZlHvt3uSnAh3o3kJHMTTb4Db9d__B0$>
June 18th, 2023, Vancouver, Canada
Deadline for submissions (extended):
March 3rd, 2023 -> extended to March 24th, 2023

Dear fellow researchers,

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 18th, in Vancouver, Canada.

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.

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.

Topics of Interests

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:

*           Computer Vision in Ultrasound Images

*           Algorithms to Mitigate Data Imbalance

*           Semi-supervised Learning in Ultrasound Images

*           Weakly-supervised Learning in Ultrasound Images

*           Supervised Learning in Ultrasound Images

*           Multi-task Learning in Ultrasound Images

*           Deep Learning in Volumetric Images

*           Data and Performance Baseline

*           Normalization Techniques in Ultrasound Image Analysis

*           Image Classification and Segmentation

*           Spatial-temporal Feature Analysis

Paper Submission

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 (https://cvpr2023.thecvf.com/Conferences/2023/AuthorGuidelines<https://urldefense.com/v3/__https:/cvpr2023.thecvf.com/Conferences/2023/AuthorGuidelines__;!!HKYIif90!xiX85HNGHmYboTJ_tMNi9_yfa2m5OB7gsaPjK7MrqymYZiJkvnZ-59sLJZlHvt3uSnAh3o3kJHMTTb4DFC2wn6k$> ). Selected papers will be presented as either oral or poster presentations and appear in the CVPR conference proceedings. Papers submission is done through the CMT system (https://cmt3.research.microsoft.com/DLUIA2023). 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.

Challenge Submission

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: https://www.cvpr2023-dl-ultrasound.com/<https://urldefense.com/v3/__https:/www.cvpr2023-dl-ultrasound.com/__;!!HKYIif90!xiX85HNGHmYboTJ_tMNi9_yfa2m5OB7gsaPjK7MrqymYZiJkvnZ-59sLJZlHvt3uSnAh3o3kJHMTTb4Db9d__B0$>

Key Dates

*           Workshop paper submission deadline (extended): March 3rd, 2023 March 24th, 2023

*           Notification of acceptance: April 3rd, 2023

*           Camera-ready submission: April 8th, 2023


cvpr2023.dl.ultrasound at gmail.com<mailto:cvpr2023.dl.ultrasound at gmail.com>
https://www.cvpr2023-dl-ultrasound.com<https://urldefense.com/v3/__https:/www.cvpr2023-dl-ultrasound.com/__;!!HKYIif90!xiX85HNGHmYboTJ_tMNi9_yfa2m5OB7gsaPjK7MrqymYZiJkvnZ-59sLJZlHvt3uSnAh3o3kJHMTTb4Db9d__B0$>


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20230314/209ccfca/attachment-0001.html>