Mr. XU Yinzhe (Shaun) our undergraduate student, has made significant research findings in the field of computer vision. Under the supervision of Prof. Sai-Kit Yeung, Shaun and his team developed a new benchmark dataset and framework for omnidirectional visual object tracking, which has been accepted by the top-tier conference International Conference on Computer Vision (ICCV) 2023. 

Visual object tracking is an important problem in computer vision with applications in video analysis, human-machine interaction, and intelligent robots. Shaun and his team found that there has been little attention paid to omnidirectional visual object tracking, although its advantages, such as stable long-term tracking and perception, are crucial in many applications. To address this gap, they proposed a new large-scale omnidirectional tracking benchmark dataset, 360VOT, with a new general tracking framework dedicated to this subfield to facilitate future research. To enable accurate performance evaluation in the subfield, they also provided four types of unbiased ground truth, including (rotated) bounding boxes and (rotated) bounding field-of-views, as well as new metrics tailored for omnidirectional images. 

Shaun will continue his studies at HKUST as a new ISD PhD student in Prof. Sai-Kit Yeung's team this year. For more information about their research, please visit the website for 360VOT: https://360vot.hkustvgd.com.

Two outstanding teams from our division showcased their entrepreneurial innovations and won championship in respective categories in the HKUST-Sino One Million Dollar Entrepreneurship Competition 2023.

The innovative start up Elevatefoods developed by Lee Kong Wai Connie, Xu Yang, Chan Yee Him Timothy, and Yuan Qiaoyaxiao Aidan has achieved remarkable success in winning the Elevator Pitch Award and the esteemed HKUST Team Awards. Under the guidance of their supervisor, Prof. Mitch LI, the students have pioneered Elevatefoods as a start up with the vision to revolutionize personalized clinical nutrition and digitally optimized food through the patented smart 3D food printing and multi-level cooking technology. Elevatefoods’ mission is to develop a commercially viable integrated smart streamlined 3D food fabrication technology that changes the way clinical nutrition foods are prepared, cooked, and experienced, hence delivering ready-to-consume personalized edible products with refined textural, sensory and nutritious profiles. The smart 3D food fabrication ecosystem enables rapid and precise food and nutrition personalization based on user’s requirement, targeting the clinical nutrition industry, including those who demand special diet needs like cancer patients, diabetes, elderlies, children, athletes and more. 

Meanwhile, the team from DAOAD, consisting of Zhang Yuruo, Gu Jingshu, Zhang Yuwei, Tommy Lam, and Gigi Lai, wins the Sustainability Impact Awards. DAOAD is supervised by Prof. Changying XIANG and Mr. Brian LAU as a rice husk upcycling company. The team combines 'rice husk' and 'sustainable development' to produce high-quality and sustainable products with rice husk waste. The team developed its own brand: DAOAD Material Technology from scratch and created rice husk-based Eco-friendly solutions, e.g. paper, bioplastic, rammed earth and polymer materials. The products are biodegradable and can be applied to different industries. The mission of DAOAD is to create a circular economy by upcycling rice husks into products and reducing carbon emissions to promote sustainability and climate actions. Their innovative project not only addresses the issue of waste management but also provides people with more choices and breathes new life into wasted resources.

We extend our warmest congratulations to the members of Elevatefoods and their supervisor, Prof. Mitch LI, for their remarkable achievements. We also congratulate the students of DAOAD and their supervisors, Prof. Changying XIANG and Mr. Brian LAU, for their outstanding accomplishments.  

Our undergraduate students Alphor CHEUNG Ho-Hin, Alan PANG Yu-Yin, Evan MA Sze-Long, Will LIU Pak-Hin and Benny SZE Chung-Lam have won the Gold Award of ASMPT Technology Award 2023, with their Final Year Project titled “Situational Awareness Location Transponder (SALT): A Phase Difference of Arrival (PDOA)-based System for Enhancing Construction Safety”, supervised by Prof. TSUI Chi-Ying and Dr. Jac LEUNG.

The team applied the Design Thinking approach to study the hazards in construction sites and construction practices. During the development of SALT, the team worked closely with engineers and safety managers from SOCAM Development Ltd. to identify the problems and design constraints through multiple rounds of interviews, site observations, and validation. SALT is a safety solution for construction sites that uses Bluetooth, Ultra-Wideband (UWB) and Inertial Measurement Units (IMU) sensing technologies to provide real-time positioning and trajectory, reducing accidents that involve heavy machinery and workers.

SALT includes tags that are placed on workers and machinery, anchors that are fixed in certain locations, and displays that give alerts and warnings. The tags and anchors use UWB technology to accurately locate their positions, while Bluetooth allows for communication over long distances. The tags also have IMUs that determine the orientation of machinery, which provides more information. This comprehensive system is designed to address the practical limitations of construction sites.

Please join us to congratulate our talented students for their hard work and dedication!

Our student of BSc in Integrative Systems and Design (ISD), Ms. CHEN Siyu, Cici won the First Runner-up award, 2023 Undergraduate Research Opportunities Program Award.

The research topic Cici working on is related to Deep Learning for Ophthalmology Image Analysis  and her project is about Image Quality-aware Diagnosis via Meta-knowledge Co-embedding.

Cici and her team reckoned that deep learning method application on high-quality (HQ) medical images have shown promising results, however, medical images usually suffer from image degradations leading to a totally different situations compared to HQ images. In clinical practices, researchers intend to filter out low-quality (LQ) images to increase the performance of deep learning method, ignoring the significant value of those LQ images. In this work, she and her team raised the problem of Image Quality-aware Diagnosis (IQAD) aiming to use LQ images and image quality labels to achieve better performance by utilizing medical images. They proposed a new method, noted as Meta-knowledge Co-embedding Network (MKCNet) for this problem, outperforming other methods.

The awarded paper has also been accepted by the top-tier conference IEEE/CVF Computer Vision and Pattern Recognition 2023. Please join us to congratulate Cici for her great job.