Andreas Møgelmose
Associate Professor at Aalborg University
Research Interests
Explore related searches
Contact this professor
Get a free first email built on one of their papers, ready for you to edit and send yourself.
Positions (1)
Andreas Møgelmose
Aalborg University
8 months ago
AI:X is a pioneering initiative at Aalborg University, Denmark, dedicated to advancing artificial intelligence research and generating real-world impact through interdisciplinary collaboration. In 2025, five new labs will be launched under AI:X, offering a total of 20 PhD stipends. The AI:Xpertise Lab, one of these, is a joint effort between the Department of Architecture, Design and Media Technology, the Technical Faculty of IT and Design, and the Department of Politics and Society, Faculty of Social Sciences and Humanities. Four PhD stipends are available in the lab, with Stipend 1 open for appointment from March 1, 2026 (or soon thereafter). This PhD position focuses on 'AI for Healthcare', specifically the automation of anesthetic pre-screenings. Auxiliary research cases may include the evaluation of laparoscopic surgery and AI assistance for spinal surgery. The lab’s mission is to integrate AI development with organizational science, investigating both technical and organizational conditions for successfully embedding AI systems in expert work environments such as healthcare. Applicants should have a strong background in software engineering or a closely related field, with substantial experience in machine learning and computer vision. Experience with large language models is considered an advantage. The position requires full-stack development skills, including the ability to build user interfaces and deploy AI systems. Given the interdisciplinary nature of the lab, candidates should be keen to collaborate with organizational researchers. Eligibility requires a Master’s degree and fulfillment of the Danish Ministerial Order No. 1039 for PhD enrollment. The stipend is funded for three years, with salary and employment terms governed by the AC collective agreement. The application must include a motivation letter, a project proposal (maximum 5 pages), CV, diplomas and transcripts, and co-author statements for any co-authored publications. Applications are to be submitted via Aalborg University’s recruitment system, accessible through the job advertisement link. The application deadline is February 5, 2026, with interviews scheduled between January 23 and February 5, 2026. The selection process involves shortlisting and assessment by qualified experts. Aalborg University values diversity and encourages applications from all backgrounds. For further information or questions, contact Associate Professor Andreas Møgelmose or AAU PhD Annemarie Davidsen via the provided emails. This opportunity is ideal for candidates passionate about deploying advanced AI solutions in healthcare, eager to work in a collaborative, interdisciplinary environment, and motivated to contribute to impactful research at a leading international university.
8 months ago
Articles (1)
We propose a fully automatic annotation scheme that takes a raw 3D point cloud with a set of fitted CAD models as input and outputs convincing point-wise labels that can be used as cheap training data for point cloud segmentation. Compared with manual annotations, we show that our automatic labels are accurate while drastically reducing the annotation time and eliminating the need for manual intervention or dataset-specific parameters. Our labeling pipeline outputs semantic classes and soft point-wise object scores, which can either be binarized into standard one-hot-encoded labels, thresholded into weak labels with ambiguous points left unlabeled, or used directly as soft labels during training. We evaluate the label quality and segmentation performance of PointNet++ on a dataset of real industrial point clouds and Scan2CAD, a public dataset of indoor scenes. Our results indicate that reducing supervision in areas that are more difficult to label automatically is beneficial compared with the conventional approach of naively assigning a hard “best guess” label to every point.
Year:
2023
Collaborators (2)
Simon Buus Jensen
Aalborg University
Galadrielle Humblot-Renaux
Aalborg University
Make your next move.
Prepare your application
Review drafts before you send them.