Blind image quality assessment via vision-language correspondence: A multitask learning perspective

W Zhang, G Zhai, Y Wei, X Yang… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
We aim at advancing blind image quality assessment (BIQA), which predicts the human
perception of image quality without any reference information. We develop a general and …

A deep learning based no-reference quality assessment model for ugc videos

W Sun, X Min, W Lu, G Zhai - Proceedings of the 30th ACM International …, 2022‏ - dl.acm.org
Quality assessment for User Generated Content (UGC) videos plays an important role in
ensuring the viewing experience of end-users. Previous UGC video quality assessment …

Blindly assess quality of in-the-wild videos via quality-aware pre-training and motion perception

B Li, W Zhang, M Tian, G Zhai… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Perceptual quality assessment of the videos acquired in the wilds is of vital importance for
quality assurance of video services. The inaccessibility of reference videos with pristine …

Blind quality assessment for in-the-wild images via hierarchical feature fusion and iterative mixed database training

W Sun, X Min, D Tu, S Ma, G Zhai - IEEE Journal of Selected …, 2023‏ - ieeexplore.ieee.org
Image quality assessment (IQA) is very important for both end-users and service providers
since a high-quality image can significantly improve the user's quality of experience (QoE) …

Image desnowing via deep invertible separation

Y Quan, X Tan, Y Huang, Y Xu… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Images taken on snowy days often suffer from severe negative visual effects caused by
snowflakes. The task of removing snowflakes from a snowy image is known as image …

Towards dimension-enriched underwater image quality assessment

Q Jiang, X Yi, L Ouyang, J Zhou… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
The absorption and scattering of light in the water medium naturally impair the quality of
underwater images, leading to multiple degradation effects including color casts, reduced …

Improved continually evolved classifiers for few-shot class-incremental learning

Y Wang, G Zhao, X Qian - … on Circuits and Systems for Video …, 2023‏ - ieeexplore.ieee.org
Few-shot class-incremental learning (FSCIL) aims to continually learn new classes using a
few samples while not forgetting the old classes. The scarcity of new training data will …

Machine-learning based monitoring of cognitive workload in rescue missions with drones

F Dell'Agnola, PK Jao, A Arza… - IEEE Journal of …, 2022‏ - ieeexplore.ieee.org
In search and rescue missions, drone operations are challenging and cognitively
demanding. High levels of cognitive workload can affect rescuers' performance, leading to …

Blind image quality assessment for authentic distortions by intermediary enhancement and iterative training

T Song, L Li, P Chen, H Liu… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
With the boom of deep neural networks, blind image quality assessment (BIQA) has
achieved great processes. However, the current BIQA metrics are limited when evaluating …

Forgetting to remember: A scalable incremental learning framework for cross-task blind image quality assessment

R Ma, Q Wu, KN Ngan, H Li, F Meng… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Recent years have witnessed the great success of blind image quality assessment (BIQA) in
various task-specific scenarios, which present invariable distortion types and evaluation …