The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Image Quality Assessment: From Mean Opinion Score to Opinion Score Distribution
Abstract
Recently, many methods have been proposed to predict the image quality which is generally described by the mean opinion score (MOS) of all subjective ratings given to an image. However, few efforts focus on predicting the opinion score distribution of the image quality ratings. In fact, the opinion score distribution reflecting subjective diversity, uncertainty, etc., can provide more subjective information about the image quality than a single MOS, which is worthy of in-depth study. In this paper, we propose a convolutional neural network based on fuzzy theory to predict the opinion score distribution of image quality. The proposed method consists of three main steps: feature extraction, feature fuzzification and fuzzy transfer. Specifically, we first use the pre-trained VGG16 without fully-connected layers to extract image features. Then, the extracted features are fuzzified by fuzzy theory, which is used to model epistemic uncertainty in the process of feature extraction. Finally, a fuzzy transfer network is used to predict the opinion score distribution of image quality by learning the mapping from epistemic uncertainty to the uncertainty existing in the image quality ratings. In addition, a new loss function is designed based on the subjective uncertainty of the opinion score distribution. Extensive experimental results prove the superior prediction performance of our proposed method.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Metrics that mirror subjective human judgment, such as the mean opinion scores (MOS) and differential mean opinion scores (DMOS), continue to serve as the benchmark for validating objective algorithms [1-3].”
From A Survey and Tutorial on Image Quality Assessment with a Contrast-Weighted Structural Similarity Framework (2026) · cites this paper as [2]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 5×
“Moreover, by looking into the performance of different backbone networks, we can find that pre-trained ResNet50+EMD loss is better than that of other baseline comparison methods on SJTU IQSD database and KonIQ-10K database.”
MethodInfluentialSelf-citationImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“Recent studies have found that using a convolutional neural network (CNN) pre-trained on relevant tasks, e.g., ImageNet [5], to extract the image features can well predict image quality.”
BackgroundDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Making a “Completely Blind” Image Quality Analyzer
Mittal, A., Soundararajan, R., & Bovik, A. C. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2012.2227726 · Cited by 6,766 · cited 3×
“In the field of IQA, predicting the MOS of image quality is very popular [1, 18, 27, 29, 32, 44, 49].”
BackgroundMethodInfluentialFSIM: A Feature Similarity Index for Image Quality Assessment
Zhang, L., Zhang, L., Mou, X., & Zhang, D. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2109730 · Cited by 5,203 · cited 1×
“According to the availability of reference information, objective IQA can be traditionally divided into full-reference (FR) IQA [48], reduced-reference (RR) IQA [46] and no-reference (NR) IQA [24].”
BackgroundInception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636 · cited 3×
“The blue triangle is the predicted [29] 0.9225 0.9265 8.7210 0.6746 0.6731 0.4097 BMPRI [27] 0.9200 0.9285 8.3407 0.4269 0.4246 0.5110 Kang [18] 0.8926 0.9049 9.5157 0.5711 0.5071 0.4993 DIQaM-NR [1] 0.9250 0.9414 8.2896 0.7901 0.7734 0.4201 WaDIQaM-NR [1] 0.9159 0.9251 9.1380 0.8484 0.8452 0.3272 SGDNet[44] 0.9159 0.…”
MethodInfluentialWhat Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
Kendall, A., & Gal, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.04977 · Cited by 3,088 · cited 1×
“It is worth noting that CNNs can also produce some uncertainty when extracting image features, which is called epistemic uncertainty [19].”
BackgroundBlind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain
Saad, M. A., Bovik, A. C., & Charrier, C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2191563 · Cited by 1,751 · cited 4×
“In the field of IQA, predicting the MOS of image quality is very popular [1, 18, 27, 29, 32, 44, 49].”
BackgroundMethodInfluentialComprehensive Survey on Distance/Similarity Measures between Probability Density Functions
Cha, S.-H. (2007) · Cited by 1,644
YFCC100M: the new data in multimedia research
Thomee, B., Shamma, D. A., Friedland, G., Elizalde, B., Ni, K., Poland, D., Borth, D., & Li, L.-J. (2016) · Communications of the ACM · doi:10.1145/2812802 · Cited by 1,541
Research works printed but not linked: 8
- Marc O Ernst and Martin S Banks . 2002. Humans integrate visual and haptic information in a statistically optimal fashion. Nature 415, 6870 ( 2002 ), 429--433. Marc O Ernst and Martin S Banks. 2002. Humans integrate visual and haptic information in a statistically optimal fashion. Nature 415, 6870 (2002), 429--433.
- Yixuan Gao , Xiongkuo Min , Wenhan Zhu , Xiao-Ping Zhang , and Guangtao Zhai . 2022. Parameterized image quality score distribution prediction. arXiv preprint arXiv:2203.00926 ( 2022 ). Yixuan Gao, Xiongkuo Min, Wenhan Zhu, Xiao-Ping Zhang, and Guangtao Zhai. 2022. Parameterized image quality score distribution prediction. arXiv preprint arXiv:2203.00926 (2022). · arXiv
- Tobias Hofeld , Poul E Heegaard , and Martin Varela . 2015 . QoE beyond the MOS: Added value using quantiles and distributions . In Int. Conf. Qual. Multimed. Exp. 1--6. Tobias Hofeld, Poul E Heegaard, and Martin Varela. 2015. QoE beyond the MOS: Added value using quantiles and distributions. In Int. Conf. Qual. Multimed. Exp. 1--6.
- Tobias Hofeld , Raimund Schatz , and Sebastian Egger . 2011 . SOS: The MOS is not enough . In Int. Conf. Qual. Multimed. Exp. 131--136 . Tobias Hofeld, Raimund Schatz, and Sebastian Egger. 2011. SOS: The MOS is not enough. In Int. Conf. Qual. Multimed. Exp. 131--136.
- Le Hou , Chen-Ping Yu , and Dimitris Samaras . 2016. Squared earth mover's distance-based loss for training deep Neural Networks. arXiv preprint arXiv:1611.05916 ( 2016 ). Le Hou, Chen-Ping Yu, and Dimitris Samaras. 2016. Squared earth mover's distance-based loss for training deep Neural Networks. arXiv preprint arXiv:1611.05916 (2016). · arXiv
- Diederik P Kingma and Jimmy Ba . 2014 . Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980 (2014). · arXiv
- Karan Mitra , Arkady Zaslavsky , and Christer Åhlund . 2014. QoE modelling, measurement and prediction: A review. arXiv preprint arXiv:1410.6952 ( 2014 ). Karan Mitra, Arkady Zaslavsky, and Christer Åhlund. 2014. QoE modelling, measurement and prediction: A review. arXiv preprint arXiv:1410.6952 (2014). · arXiv
- Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014). · arXiv
Cited by
Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild
Min, X., Gao, Y., Cao, Y., Zhai, G., Zhang, W., Sun, H., & Chen, C. W. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3544659 · Cited by 181
“…Evaluation Criteria: When predicting the MOS of image quality, we use BRISQUE [27], NIQE [26], BMPRI [62], CNNIQA [63], (Wa)DIQaM-N [9], DBCNN [34], HyperIQA [37], TReS [35], DACNN [36], GraphIQA [64], NIMA [46], Gao [45], StairIQA [39], REQA [38], VIPNet [65], and TOPIQ [66] as competing methods.”
InfluentialSelf-citationQuality-aware Pretrained Models for Blind Image Quality Assessment
Zhao, K., Yuan, K., Sun, M. B., Li, M., & Wen, X. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02136 · Cited by 162
A Perceptual Quality Assessment Exploration for AIGC Images
Zhang, Z., Li, C., Sun, W., Liu, X., Min, X., & Zhai, G. (2023) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew59549.2023.00082 · Cited by 166
Self-citationEficient image denoising using deep learning: A brief survey
Jiang, B., Li, J., Lu, Y., Cai, Q., Song, H., & Lu, G. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103013 · Cited by 72
Self-citationBlind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality Token
Shi, J., Gao, P., & Smolić, A. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3325719 · Cited by 57
“Due to the richer subjective information contained in score distributionscomparedtoMOS,andtheabilityofratingdistribu-tionstodescribeimagequality,itispossibletodesignobjective methods[41],[42],[43]forpredictingratingdistributions.”
Background
Metadata
- Authors
- Gao, Y., Min, X., Zhu, Y., Li, J., Zhang, X.-P., & Zhai, G.
- Affiliations
- Shanghai Jiao Tong University (CN)
- Alibaba Group (China) (CN)
- Toronto Metropolitan University (CA)
- Venue
- Proceedings of the 30th ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2022-10-10
- Pages
- 997-1005
- OpenAlex
- W4304098873
- Cited by
- 58
- References
- 39
- Citations by year
- 2026: 7 · 2025: 21 · 2024: 12 · 2023: 17 · 2022: 1
- FWCI
- 4.62
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Conference on Multimedia (ACM MM) (publishedVersion)
- Funders
- National Key R & D Program of China (2021YFE0206700)
- NSFC (61831015, 61901260)
- Alibaba Group through Alibaba Innovative Research Program
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- image quality assessment, mean opinion score, subjective quality prediction, epistemic uncertainty, loss function design
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Image Quality Assessment: From Mean Opinion Score to Opinion Score Distribution. https://app.cochat.ai/papers/10.1145/3503161.3547872
- The paper
- Gao, Y., Min, X., Zhu, Y., Li, J., Zhang, X.-P., & Zhai, G. (2022). Image Quality Assessment: From Mean Opinion Score to Opinion Score Distribution. Proceedings of the 30th ACM International Conference on Multimedia. https://doi.org/10.1145/3503161.3547872
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.