Prof. Ying Bi

Zhengzhou University, China

Bi Ying, PhD, Distinguished Professor, selected by National Young Talent Program. She received her PhD from Victoria University of Wellington, New Zealand, where she studied under Professor MengjieZhang (Fellow of the Royal New Zealand Academy of Sciences, Fellow of the New Zealand Academy of Engineering, IEEEFellow) and Professor BingXue (Fellow of the New Zealand Academy of Engineering and Associate Dean of the School of Engineering and Computing, Victoria University of Wellington).  She has been engaged in theoretical and applied research in genetic programming, evolutionary computing, machine learning, computer vision and other fields for a long time, published the world's first English monograph on image classification based on genetic programming, published 55 academic papers in international academic journals and conferences, including 25 SCI journal articles, published 16 papers as the first or corresponding author of TOP journals of the first region of the Chinese Academy of Sciences.15 in the IEEE Journal series. Ranked 93rd (> 16,000 researchers) on TheGPBibliography, the website for global genetic planning algorithms. Served as the guest editor of AppliedSoftComputing and MemeticComputing, the SCI Region I journals. Organized the workshop on evolutionary data mining and machine learning in IEEE International Data Mining Conference (2021, 2022) for two consecutive years. She is the Vice Chair of the IEEECIS Symposium on Evolutionary Computer Vision and Image Processing, a member of the IEEE CIS Symposium on Evolutionary Feature Selection and Construction, and has organized several relevant symposiums at the famous international conferences on evolutionary computing, such as IEEE CEC and IEEE SSCI. She has been the reviewer of important journals in more than 20 fields and the member of the program committee of more than 20 internationally renowned academic conferences. Member of the IEEE Women in Computing Intelligence Committee, Chair of the 2024 International Conference on Evolutionary Computing (IEEE CEC) Symposium, Vice President of Student Affairs for the 2023 Conference on Genetic and Evolutionary Computing (GECCO), Participated in the organization of two international academic conferences IEEE CEC 2019 and Australasian AI 2018.

Assoc.Prof. Lei Chen

Shandong University, China

Lei Chen received the B.Sc. and M.Sc. degrees in electrical engineering from Shandong University, Jinan, China, and the Ph.D. degree in electrical and computer engineering from University of Ottawa, Ontario, Canada. He is currently an Associate Professor with the School of Information Science and Engineering, Shandong University, China. His research interests include image processing and computer vision, visual quality assessment and pattern recognition, machine learning and artificial intelligence. He was the principal investigator of projects granted from the National Natural Science Foundation of China, National Natural Science Foundation of Shandong Province, China Postdoctoral Science Foundation, etc. He has published more than 40 papers on top international journals and conferences in recent years including IEEE TIP, Signal Process., ICME, etc. He was awarded the Future Plan for Young Scholars of Shandong University. He served for the ICIGP 2021, ICIGP 2022, IoTCIT 2022, MLCCIM 2022, etc. as Technical Co-Chair or Publicity Co-Chair.

Title: New Advances in Deep Learning-Based Perceptual Image Quality Assessment

Abstract: In recent years, image quality assessment (IQA) has become an important task in multimedia communication, medical imaging, remote sensing, and other visual applications. No-reference IQA (NR-IQA), which predicts image quality without reference images, remains challenging due to diverse distortions, complex local degradations, and the difficulty of jointly modeling distortion-sensitive and semantic information. To address these challenges, we propose two NR-IQA frameworks, MDM-GFIQA and DAFSMamba. MDM-GFIQA integrates multi-scale adaptive feature modulation with degradation-aware feature fusion to enhance the modeling of quality-relevant local features and degradation semantics. DAFSMamba introduces a distortion-aware frequency selection mechanism to adaptively capture perceptually relevant frequency components, and further combines Vision Mamba-based global modeling with token-wise semantic aggregation for effective frequency, spatial, and semantic representation. Extensive experiments on synthetic and authentic distortion datasets demonstrate the effectiveness of the proposed methods in image quality prediction, robustness, and cross-dataset generalization. These studies provide effective approaches for perceptual image quality assessment and contribute to the development of more robust and accurate visual quality modeling.