KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment

V Hosu, H Lin, T Sziranyi… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Deep learning methods for image quality assessment (IQA) are limited due to the small size
of existing datasets. Extensive datasets require substantial resources both for generating …

The Konstanz natural video database (KoNViD-1k)

V Hosu, F Hahn, M Jenadeleh, H Lin… - … on quality of …, 2017 - ieeexplore.ieee.org
Subjective video quality assessment (VQA) strongly depends on semantics, context, and the
types of visual distortions. Currently, all existing VQA databases include only a small number …

KonIQ-10K: Towards an ecologically valid and large-scale IQA database

H Lin, V Hosu, D Saupe - arXiv preprint arXiv:1803.08489, 2018 - arxiv.org
The main challenge in applying state-of-the-art deep learning methods to predict image
quality in-the-wild is the relatively small size of existing quality scored datasets. The reason …

Analysis of video quality datasets via design of minimalistic video quality models

W Sun, W Wen, X Min, L Lan, G Zhai… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Blind video quality assessment (BVQA) plays an indispensable role in monitoring and
improving the end-users' viewing experience in various real-world video-enabled media …

Deep face recognition with center invariant loss

Y Wu, H Liu, J Li, Y Fu - Proceedings of the on Thematic Workshops of …, 2017 - dl.acm.org
Convolutional Neural Networks (CNNs) have been widely used for face recognition and got
extraordinary performance with large number of available face images of different people …

Troubleshooting blind image quality models in the wild

Z Wang, H Wang, T Chen… - Proceedings of the …, 2021 - openaccess.thecvf.com
Recently, the group maximum differentiation competition (gMAD) has been used to improve
blind image quality assessment (BIQA) models, with the help of full-reference metrics. When …

Group happiness assessment using geometric features and dataset balancing

V Vonikakis, Y Yazici, VD Nguyen… - Proceedings of the 18th …, 2016 - dl.acm.org
This paper presents the techniques employed in our team's submissions to the 2016
Emotion Recognition in the Wild contest, for the sub-challenge of group-level emotion …

User-generated video quality assessment: A subjective and objective study

Y Li, S Meng, X Zhang, M Wang, S Wang… - IEEE Transactions …, 2021 - ieeexplore.ieee.org
Recently, we have observed an exponential increase of user-generated content (UGC)
videos. The distinguished characteristic of UGC videos originates from the video production …

UGC-VIDEO: Perceptual quality assessment of user-generated videos

Y Li, S Meng, X Zhang, S Wang… - 2020 IEEE Conference …, 2020 - ieeexplore.ieee.org
Recent years have witnessed an ever-expanding volume of user-generated content (UGC)
videos available on the Internet. Nevertheless, progress on perceptual quality assessment of …

Learning from synthetic data for opinion-free blind image quality assessment in the wild

Z Wang, ZR Tang, J Zhang, Y Fang - arXiv preprint arXiv:2106.14076, 2021 - arxiv.org
Nowadays, most existing blind image quality assessment (BIQA) models 1) are developed
for synthetically-distorted images and often generalize poorly to authentic ones; 2) heavily …