Room “Sala Seminari” - Abacus Building (U14)
Visual quality assessment using crowdsourcing
Speaker
Dr Hanhe Lin
Assistant professor - School of Science and Engineering, University of Dundee – Great Britain
Abstract
Deep learning (DL) has achieved promising results in many computer vision tasks such as object detection, medical image analysis, etc. State-of-the-art DL models usually have many parameters requiring massive amounts of data to train from scratch, whereas the existing visual quality assessment datasets are usually small due to assessing the quality of a very large number of stimuli in a lab setting would require too many participants and too much time for preparing and running the experiment. In this talk, I will give a brief introduction how we designed a reliable and efficient framework for conducting subjective visual quality assessment via crowdsourcing, based on that a few large-scale benchmarking datasets and models have been developed for various visual quality assessment tasks, such as image/video quality assessment and just noticeable difference for image compression.
Short bio
Hanhe Lin received his PhD degree from the University of Otago in 2016. He was then a postdoc researcher at University of Konstanz until 2021. After being a senior research fellow at National Subsea Centre in Robert Gordon University of a short period, he is currently a Lecturer in Computing at the School of Science and Engineering, University of Dundee. His research interests include visual quality assessment, medical image analysis, and machine learning. Lin has published more than 60 peer-reviewed papers in his research domains. He is an IEEE Senior member and an EPSRC Peer Review College member. He also served as a member of the technical program committee or a reviewer in numerous conferences such as ICME, ICIP, ICASSP, and QoMEX. Since 2016, he has been serving regularly as a reviewer for journals such as IEEE Trans. Pattern Analysis and Machine Intelligence, IEEE Trans. Image Processing, and IEEE Trans. Multimedia. Currently, he is serving as guest editor for the MDPI Journal of Imaging and associate editor for the Frontier in Imaging.
contact person for this Seminar: luigi.celona@unimib.it