Multiscale structural similarity for image quality assessment
The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index; none of the 14 sources its claims cite is checked for support yet.
Abstract
The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multiscale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions. We develop an image synthesis method to calibrate the parameters that define the relative importance of different scales. Experimental comparisons demonstrate the effectiveness of the proposed method.
Overview
CoChat Summary
TL;DR
This paper proposes a multi-scale structural similarity (MS-SSIM) image quality method that combines contrast and structure comparisons across scales and luminance comparison at the coarsest scale. On the LIVE JPEG/JPEG2000 database, MS-SSIM outperformed PSNR, the Sarnoff model, and single-scale SSIM variants on all reported evaluation criteria.
Key findings
- MS-SSIM achieved the best reported performance: CC 0.969, ROCC 0.966, MAE 3.86, RMS 4.91, and OR 1.16%, compared with the best single-scale SSIM at M=2 (CC 0.963, ROCC 0.959, MAE 4.21, RMS 5.38, OR 2.62%) and PSNR (CC 0.905, ROCC 0.901, MAE 6.53, RMS 8.45, OR 15.7%).
- Single-scale SSIM performance varied with scale; the best single-scale result was at M=2, and single-scale SSIM tended to give higher scores as scale increased.
- The calibrated cross-scale exponents were β1=γ1=0.0448, β2=γ2=0.2856, β3=γ3=0.3001, β4=γ4=0.2363, and α5=β5=γ5=0.1333.
- The authors conclude that multi-scale SSIM provides a meaningful balance between scales and outperforms the best single-scale SSIM and state-of-the-art image quality metrics.
Methods
- The MS-SSIM system iteratively applies a low-pass filter and downsamples by 2; at each scale it computes contrast and structure comparisons, computes luminance comparison only at Scale M, and combines them using exponents normalized so that ∑γj=1.
- Cross-scale parameters were calibrated by image synthesis: 5 scales and 12 distortion levels (range 2^3 to 2^14) were used with 10 original 64×64 images, producing 600 distorted images; 8 subjects selected images of equal perceived quality across scales at a viewing distance of 32 pixels per degree of visual angle.
- Evaluation used the LIVE database with 344 JPEG and JPEG2000 compressed images (bit rate 0.028 to 3.150 bits/pixel), MOS from 13–25 subjective scores, and compared PSNR, Sarnoff JNDmetrix 8.0, single-scale SSIM for M=1–5, and MS-SSIM using CC, MAE, RMS, OR, and ROCC after logistic mapping.
Limitations
- Stated: the image-synthesis calibration approach is “still rather crude,” and the authors are working on a more systematic approach.
- Stated: CSF cannot be directly used to derive the parameters because it is typically measured at visibility threshold with simplified stimuli, whereas the goal is comparing complex structured images at visible distortion levels.
- Evident from the text: calibration used only 10 original 64×64 grayscale images and 8 subjects, including one author, and evaluation was limited to the LIVE JPEG/JPEG2000 database.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 1 Not valid · 14 Not checked · 18 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It can also be observed that the single-scale model tends to supply higher scores with the increase of scales.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Finally, for every one of the objective evaluation criteria, multi-scale SSIM model outperforms all the other models, including the best single-scale SSIM model, suggesting a meaningful balance between scales.”
- Also stated in: § 5. DISCUSSIONS · p. 4 · hedged
“Experiments show that with an appropriate parameter settings, the multi-scale method outperforms the best single-scale SSIM model as well as state-of-the-art image quality metrics.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 5. DISCUSSIONS · p. 4 · hedged
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In general, the subjects agreed with each other on each image more than they agreed with themselves across different images.”
plainstates an associationn = 8- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The resulting parameters we obtained are β 1 = γ 1 = 0.0448, β 2 = γ 2 = 0.2856, β 3 = γ 3 = 0.3001, β 4 = γ 4 = 0.2363, and α 5 = β 5 = γ 5 = 0.1333, respectively.”
plainn = 8- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“However, the SSIM index algorithm introduced in [5] is a single-scale approach.”
What the sources say
- Not matchedcites [5] [5] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, 'Image quality assessment: From error measurement to structural similarity,' IEEE Trans. Image Processing , vol. 13, Jan. 2004. -
More than one paper fits this citation.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
10 more claims
Create a free account to see all 33 claims and every source verdict.
- It may state two separate claims as one. 8
- Probably not a substantial claim. 13
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?
The cited source says what the claim attributes to it.
In the citing paper
“Further, as research in quality assessment has demonstrated, incorporating multiscale information when assessing quality produces QA algorithms that perform better in terms of correlation with human perception [13], [29].”
From No-Reference Image Quality Assessment in the Spatial Domain (2012) · cites this paper as [13]
Citations
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
Self-citationA universal image quality index
Wang, Z., & Bovik, A. C. (2002) · IEEE Signal Processing Letters · doi:10.1109/97.995823 · Cited by 5,757
Self-citationImage quality measures and their performance
Eskicioglu, A. M., & Fisher, P. S. (1995) · IEEE Transactions on Communications · doi:10.1109/26.477498 · Cited by 2,117 · cited 1×
“Traditional perceptual image quality assessment methods are based on a bottom-up approach which attempts to simulate the functionality of the relevant early human visual system (HVS) components.”
BackgroundA Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients
Portilla, J., & Simoncelli, E. P. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026553619983 · Cited by 1,806 · cited 2×
“These synthesis methods provide a powerful and efficient means of testing a model, and have the added benefit that the resulting images suggest improvements that might be made to the model [11].”
MethodSelf-citation(1995) · Medical Entomology and Zoology · Cited by 1,212
Pyramid-based texture analysis/synthesis
Heeger, D. J., & Bergen, J. R. (1995) · Proceedings of the 22nd annual conference on Computer graphics and interactive techniques - SIGGRAPH '95 · doi:10.1145/218380.218446 · Cited by 1,095
Video quality assessment based on structural distortion measurement
Wang, Z., Lu, L., & Bovik, A. C. (2004) · Signal Processing: Image Communication · doi:10.1016/s0923-5965(03)00076-6 · Cited by 1,024
Self-citationImage Quality Assessment: From Error Measurement to Structural Similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · Cited by 919
Self-citationTeo, P. C., & Heeger, D. J. (2002) · Proceedings of 1st International Conference on Image Processing · doi:10.1109/icip.1994.413502 · Cited by 471
Objective video quality assessment
(2003) · Handbook of Video Databases · doi:10.1201/9780203489864-45 · Cited by 359
Research works printed but not linked: 2
- 0, JNDmetrix Technology, Sarnoff Corporation
- 2000, Final report from the video quality experts group on the validation of objective models of video quality assessment, VQEG
Cited by
Items 201–300 of 6,047
Shao, F., Lin, W., Gu, S., Jiang, G., & Srikanthan, T. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2240003 · Cited by 191
OFDM-Guided Deep Joint Source Channel Coding for Wireless Multipath Fading Channels
Yang, M., Bian, C., & Kim, H.-S. (2022) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2022.3151935 · Cited by 191
“In Figure 14, we show the comparison between our JSCC and conventional schemes in PSNR and MS-SSIM [53].”
MethodInfluentialGenerative Joint Source-Channel Coding for Semantic Image Transmission
Erdemir, E., Tung, T.-Y., Dragotti, P. L., & Gündüz, D. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3288243 · Cited by 190
“Similar to [6], we use the default parameters for (αM , βj , γj) in the original paper [35].”
MethodTwo-Stream Convolutional Networks for Blind Image Quality Assessment
Yan, Q., Gong, D., & Zhang, Y. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2883741 · Cited by 181
“Moreover, we let our method play the group MAximum Differentiation (gMAD) competition game [52] with two stateof-the-art NR-IQA methods MEON [25] and deepIQA [26] and one FR-IQA method MS-SSIM [6].”
MethodPQA-Net: Deep No Reference Point Cloud Quality Assessment via Multi-View Projection
Liu, Q., Yuan, H., Su, H., Liu, H., Wang, Y., Yang, H., & Hou, J. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3100282 · Cited by 184
Learning to generate images with perceptual similarity metrics
Snell, J., Ridgeway, K., Liao, R., Roads, B. D., Mozer, M. C., & Zemel, R. S. (2017) · 2017 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2017.8297089 · Cited by 186
ViS3: an algorithm for video quality assessment via analysis of spatial and spatiotemporal slices
Vu, P. V., & Chandler, D. M. (2014) · Journal of Electronic Imaging · doi:10.1117/1.jei.23.1.013016 · Cited by 185
Mean Deviation Similarity Index: Efficient and Reliable Full-Reference Image Quality Evaluator
Ziaei Nafchi, H., Shahkolaei, A., Hedjam, R., & Cheriet, M. (2016) · IEEE Access · doi:10.1109/access.2016.2604042 · Cited by 182
“Twelve state-of-the-art IQA models were chosen for comparison [7], [9], [12], [15], [16], [18]–[23], [44] including the most recent indices in literature [19]–[23], [44].”
BackgroundMethodA Quality-of-Experience Index for Streaming Video
Duanmu, Z., Zeng, K., Ma, K., Rehman, A., & Wang, Z. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2016.2608329 · Cited by 185
“Among the eight QoE models, four VQA algorithms including PSNR, SSIM [8], MS-SSIM [9] and SSIMplus [12], are employed as the framelevel video presentation quality measures.”
BackgroundMethodInfluentialSelf-citationLeinonen, J., Nerini, D., & Berne, A. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3032790 · Cited by 184
“To evaluate if the generated images properly reproduce the spatial structure of the true images, we also compute the multiscale structural similarity index (MS-SSIM), as defined in [41], and the log spectral distance (LSD) that gives the difference of the power spectra in decibels (dB) LSD = √√√ 1 N N ∑”
MethodDeep learning for video compressive sensing
Qiao, M., Meng, Z., Ma, J., & Yuan, X. (2020) · APL Photonics · doi:10.1063/1.5140721 · Cited by 179
ESIM: Edge Similarity for Screen Content Image Quality Assessment
Ni, Z., Ma, L., Zeng, H., Chen, J., Cai, C., & Ma, K.-K. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2718185 · Cited by 184
Learning End-to-End Lossy Image Compression: A Benchmark
Hu, Y., Yang, W., Ma, Z., & Liu, J. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3065339 · Cited by 181
“Because end-to-end learned models can be tuned with both PSNR and MS-SSIM, we are able to investigate the relationship between different metrics and objectives.”
MethodInfluentialQuality Assessment of Deblocked Images
Yim, C., & Bovik, A. C. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2061859 · Cited by 178
Self-citationDash, A., Ye, J., & Wang, G. (2024) · IEEE Access · doi:10.1109/access.2023.3346273 · Cited by 211
“Multi-Scale SSIM or MS-SSIM [37] is a multiscale version of SSIM that allows for more flexibility in incorporating image resolution and viewing conditions than a single scale approach.”
A spatiotemporal most-apparent-distortion model for video quality assessment
Vu, P. V., Vu, C. T., & Chandler, D. M. (2011) · 2011 18th IEEE International Conference on Image Processing · doi:10.1109/icip.2011.6116171 · Cited by 180
“, MS-SSIM [3], VSNR [4]).”
QoE Modeling for HTTP Adaptive Video Streaming–A Survey and Open Challenges
Barman, N., & Martini, M. G. (2019) · IEEE Access · doi:10.1109/access.2019.2901778 · Cited by 178
“The authors evaluate 6 objective IQA metrics (PSNR, PSNRHVS [95], SSIM, MS-SSIM [96], NIQE [43] and GMSD [97]) and two VQA metrics (VMAF [98] and STRRED [89]) on the subjective dataset and it is observed that STRRED gives the highest performance in terms of SROCC considering both a subset of the…”
MethodBrooks, A. C., Zhao, X., & Pappas, T. N. (2008) · IEEE Transactions on Image Processing · doi:10.1109/tip.2008.926161 · Cited by 175
Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesis
Hu, S., Lei, B., Wang, S., Wang, Y., Feng, Z., & Shen, Y. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3107013 · Cited by 176
“where l M and cs j are the terms we defined in SSIM at scale M and j , respectively. α and β j are the constants used to adjust the relative importance of different components, according to [39].”
MethodHDR-VQM: An objective quality measure for high dynamic range video
Narwaria, M., Perreira Da Silva, M., & Le Callet, P. (2015) · Signal Processing: Image Communication · doi:10.1016/j.image.2015.04.009 · Cited by 176
“We compared the performance of HDR-VQM with a few popular LDR methods including PSNR and multi-scale SSIM [11].”
MethodInfluentialMuLoG, or How to Apply Gaussian Denoisers to Multi-Channel SAR Speckle Reduction?
Deledalle, C.-A., Denis, L., Tabti, S., & Tupin, F. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2713946 · Cited by 176
“For this reason, we have also included SSIM [66] values.”
MethodLiu, R. W., Guo, Y., Lu, Y., Chui, K. T., & Gupta, B. B. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3170594 · Cited by 175
Ten years of generative adversarial nets (GANs): a survey of the state-of-the-art
Chakraborty, T., Reddy K S, U., Naik, S. M., Panja, M., & Manvitha, B. (2024) · Machine Learning: Science and Technology · doi:10.1088/2632-2153/ad1f77 · Cited by 174
“The multi-scale structural similarity metric (MS-SSIM), an extension of the traditional structural similarity index (SSIM), serves as an effective measure for evaluating the quality of GAN-generated images [209].”
MethodA Multiscale Metric for 3D Mesh Visual Quality Assessment
Lavoué, G. (2011) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2011.02017.x · Cited by 171
Testing Deep Neural NetworksPreprint
Sun, Y., Huang, X., Kroening, D., Sharp, J., Hill, M., & Ashmore, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.04792 · Cited by 167
“For the general case, the function g ( ψ k,l , x 1 , x 2 ) can express the distance be-tween two vectors a real number d and a distance measure L p , or structural similarity distances such as SSIM [23].”
BackgroundReparameterizing discontinuous integrands for differentiable rendering
Loubet, G., Holzschuch, N., & Jakob, W. (2019) · ACM Transactions on Graphics · doi:10.1145/3355089.3356510 · Cited by 164
“…of this type of reconstruction are conceivable: for instance, instead of pixel-wise losses, it would likely be preferable to use richer metrics such as structural similarity [Wang et al. 2003] or pre-trained layers from a convolutional neural network such as VGG [Simonyan and Zisserman 2015].”
Perceptual Quality Assessment of Colored 3D Point Clouds
Liu, Q., Su, H., Duanmu, Z., Liu, W., & Wang, Z. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3167151 · Cited by 171
“In addition to the aforementioned point-based models, there are also many projection-based models [12], [21], [23], [32], [45], [52], [53], [58], such as projection-based PSNR (PSNRp) [12], [32], projection-based structural similarity (SSIMp) [12], [32], [69], projection-based multi-scale structural similarity (MS-SSI…”
BackgroundSelf-citationBeamforming and Speckle Reduction Using Neural Networks
Hyun, D., Brickson, L. L., Looby, K. T., & Dahl, J. J. (2019) · IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control · doi:10.1109/tuffc.2019.2903795 · Cited by 170
“The different scales can be achieved either by downsampling the image [22] or by changing the standard deviation parameter of the Gaussian filter [21].”
Blindly Assess Quality of In-the-Wild Videos via Quality-Aware Pre-Training and Motion Perception
Li, B., Zhang, W., Tian, M., Zhai, G., & Wang, X. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3164467 · Cited by 171
“Specifically, similar to [12], we generate pseudo-labels for KADIS-700k [78] using MS-SSIM [79], and use them to pre-train a ResNet50 in a regression manner (dubbed as SFR).”
MethodQuality Prediction of Asymmetrically Distorted Stereoscopic 3D Images
Wang, J., Rehman, A., Zeng, K., Wang, S., & Wang, Z. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2446942 · Cited by 165
“The subjective test was conducted in the Lab for Image and Vision Computing at University of Waterloo.”
MethodSelf-citationReduced-Reference Image Quality Assessment With Visual Information Fidelity
Wu, J., Lin, W., Shi, G., & Liu, A. (2013) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2013.2266093 · Cited by 168
“On TID database (as shown in Table II), the proposed index performs much better on fourteen out of seventeen types of distortion than WNISM and RRED, and is comparable with the two FR-IQA indices (i.e., PSNR and MS-SSIM) on almost all of the types of distortion.”
BackgroundMethodInfluentialPerceptual Image Quality Assessment with Transformers
Cheon, M., Yoon, S.-J., Kang, B., & Lee, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00054 · Cited by 168
“For each distorted image, predicted scores of PSNR, SSIM [51], MS-SSIM [52], LPIPS [61], and proposed IQT are listed.”
BackgroundMethodInfluentialDehazing Evaluation: Real-World Benchmark Datasets, Criteria, and Baselines
Zhao, S., Zhang, L., Huang, S., Shen, Y., & Zhao, S. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2995264 · Cited by 169
“In a later work of Wang et al. , multiscale (MS) information was introduced in the SSIM, and MS-SSIM [17] was proposed.”
Content-partitioned structural similarity index for image quality assessment
Li, C., & Bovik, A. C. (2010) · Signal Processing: Image Communication · doi:10.1016/j.image.2010.03.004 · Cited by 168
Self-citationFAMM: Facial Muscle Motions for Detecting Compressed Deepfake Videos Over Social Networks
Liao, X., Wang, Y., Wang, T., Hu, J., & Wu, X. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3278310 · Cited by 169
“We use Peak Signal to Noise Ratio (PSNR) [42], Structural Similarity (SSIM) [43], Visual Information Fidelity (VIF) [44], and Relative Polar Edge Coherence (RECO) [45] to measure the video quality.”
MethodPerceptual image quality assessment using a normalized Laplacian pyramid
Laparra, V., Ballé, J., Berardino, A., & Simoncelli, E. P. (2016) · Electronic Imaging · doi:10.2352/issn.2470-1173.2016.16.hvei-103 · Cited by 161
Self-citationLight Field Reconstruction Using Convolutional Network on EPI and Extended Applications
Wu, G., Liu, Y., Fang, L., Dai, Q., & Chai, T. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2845393 · Cited by 164
“The quality of the synthesized views is measured by the PSNR and MS-SSIM [43] against the ground truth image.”
MethodInfluentialA Metric for Light Field Reconstruction, Compression, and Display Quality Evaluation
Min, X., Zhou, J., Zhai, G., Le Callet, P., Yang, X., & Guan, X. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2966081 · Cited by 167
A comprehensive review of deep learning-based single image super-resolution
Bashir, S. M. A., Wang, Y., Khan, M., & Niu, Y. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.621 · Cited by 172
RetractedLightingNet: An Integrated Learning Method for Low-Light Image Enhancement
Yang, S., Zhou, D., Cao, J., & Guo, Y. (2023) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2023.3240087 · Cited by 168
“…Peak signal-noise ratio (PSNR) [60], Structural similarity (SSIM) [60], Pixel-based visual information fidelity (VIF) [61], Universal quality image index (UQI) [62], Multi-scale structural similarity index (MS-SSIM) [63], Spatial correlation coefficient (SCC) [64], Spectral angle mapper (SAM) [65].”
BackgroundEdge Strength Similarity for Image Quality Assessment
Zhang, X., Feng, X., Wang, W., & Xue, W. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2013.2244081 · Cited by 166
Structural similarity index family for image quality assessment in radiological images
Renieblas, G. P., Nogués, A. T., González, A. M., Gómez-Leon, N., & del Castillo, E. G. (2017) · Journal of Medical Imaging · doi:10.1117/1.jmi.4.3.035501 · Cited by 166
Blind omnidirectional image quality assessment with viewport oriented graph convolutional networks
Xu, J., Zhou, W., & Chen, Z. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3015186 · Cited by 166
Blind Image Quality Assessment Based on Multichannel Feature Fusion and Label Transfer
Wu, Q., Li, H., Meng, F., Ngan, K. N., Luo, B., Huang, C., & Zeng, B. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2412773 · Cited by 164
“In addition, we also implement the onesided t-test on the MOS and MS-SSIM of all denoised images.”
MethodAnalysis of Distortion Distribution for Pooling in Image Quality Prediction
Gu, K., Wang, S., Zhai, G., Lin, W., Yang, X., & Zhang, W. (2016) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2015.2511624 · Cited by 164
“By a psychophysical test [18], {γ1, .”
BackgroundMethodInfluentialZhang, S., Wijesinghe, A., & Ding, Z. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3278235 · Cited by 169
AR-Net: Adaptive Attention and Residual Refinement Network for Copy-Move Forgery Detection
Zhu, Y., Chen, C., Yan, G., Guo, Y., & Dong, Y. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2982705 · Cited by 162
“SSIM loss can capture the structural information and take into account the local neighborhood of each pixel, which is a measure in the patch level [28].”
BackgroundMethodVideo Generative Adversarial Networks: A Review
Aldausari, N., Sowmya, A., Marcus, N., & Mohammadi, G. (2023) · ACM Computing Surveys · doi:10.1145/3487891 · Cited by 162
“For quantitative measures, Inception Score (IS) [104], Fréchet Inception Distance (FID) [105], Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM) [106], and Mean Squared Error (MSE) [107] are prevalent for video GANs.”
BackgroundHybrid deep learning architecture for rail surface segmentation and surface defect detection
Wu, Y., Qin, Y., Qian, Y., Guo, F., Wang, Z., & Jia, L. (2022) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12710 · Cited by 162
“SSIM index can capture the structural information from an image and was originally proposed to assess image quality (Z. Wang et al., 2003).”
BackgroundSelf-citationA comprehensive review of past and present image inpainting methods
Jam, J., Kendrick, C., Walker, K., Drouard, V., Hsu, J. G.-S., & Yap, M. H. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2020.103147 · Cited by 160
Perceptual Quality Assessment of Omnidirectional Images
Duan, H., Zhai, G., Min, X., Zhu, Y., Fang, Y., & Yang, X. (2018) · 2018 IEEE International Symposium on Circuits and Systems (ISCAS) · doi:10.1109/iscas.2018.8351786 · Cited by 156
A reference-free underwater image quality assessment metric in frequency domain
Yang, N., Zhong, Q., Li, K., Cong, R., Zhao, Y., & Kwong, S. (2021) · Signal Processing: Image Communication · doi:10.1016/j.image.2021.116218 · Cited by 158
Scalable Image Coding for Humans and Machines
Choi, H., & Bajic, I. V. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3160602 · Cited by 161
AnonymousNet: Natural Face De-Identification With Measurable Privacy
Li, T., & Lin, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00013 · Cited by 166
“7894 MS-SSIM [59] 0.”
An Iterative Mean Filter for Image Denoising
erkan, U., Thanh, D. N. H., Hieu, L. M., & Enginoglu, S. (2019) · IEEE Access · doi:10.1109/access.2019.2953924 · Cited by 159
“MSSIM is better than SSIM in terms of its correlation with a human judgment of the images [42].”
BackgroundMethodInfluentialJin, X., Yi, K., & Xu, J. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3180274 · Cited by 158
“SSIM loss [53] measures the structural similarity between prediction and ground truth, which can be calculated as, , (18) where μ S , μ G and σ S , σ G are the means and the standard deviations of two patches from the predicted S and the ground truth G , respectively. σ SG is the covariance.”
BackgroundFovVideoVDP: a visible difference predictor for wide field-of-view video
Mantiuk, R. K., Denes, G., Chapiro, A., Kaplanyan, A., Rufo, G., Bachy, R., Lian, T., & Patney, A. (2021) · ACM Transactions on Graphics · doi:10.1145/3450626.3459831 · Cited by 160
Adler, A., Araya‐Polo, M., & Poggio, T. (2021) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.3037429 · Cited by 168
“To optimize the visual quality of the reconstructed models, a mixed loss function was implemented, composed by the MSE and MSSIM [56] with five image scales, and the network was trained using a data set of 12,000 synthetic models.”
MethodHigh-resolution neural face swapping for visual effects
Naruniec, J., Helminger, L., Schroers, C., & Weber, R. M. (2020) · Computer Graphics Forum · doi:10.1111/cgf.14062 · Cited by 154
Ren, T., Xu, H., Jiang, G., Yu, M., Zhang, X., Wang, B., & Luo, T. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3205061 · Cited by 221
SpEED-QA: Spatial Efficient Entropic Differencing for Image and Video Quality
Bampis, C. G., Gupta, P., Soundararajan, R., & Bovik, A. C. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2726542 · Cited by 150
“The values computed at each scale can be combined, e.g., by using the perceptually optimized exponent weights used in MS-structural similarity (SSIM) [31].”
MethodInfluentialSelf-citationPIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
Ignatov, A., Timofte, R., Vu, T., Luu, T. M., Pham, T. X., Nguyen, C. V., Kim, Y., Choi, J.-S., Kim, M., Huang, J., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_20 · Cited by 169
“….pb files that were later run on the test images and validated based on three metrics: • Their speed on HD-resolution (1280 × 720 pixels) images measured compared to the baseline SRCNN [8] network, • PSNR metric measuring their fidelity score, • MS-SSIM [37] metric measuring their perceptual score.”
MethodFew-Shot Scene-Adaptive Anomaly Detection
Lu, Y., Yu, F., Reddy, M. K. K., & Wang, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58558-7_8 · Cited by 205
“We define L(·) by combine the least absolute deviation (L1 loss) [28], multi-scale structural similarity measurement (Lssm loss) [39] and gradient difference (Lgdl loss) [21]:”
MethodPIPAL: A Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration
Gu, J., Cai, H., Chen, H., Ye, X., Ren, J., & Dong, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58621-8_37 · Cited by 296
“For the FR-IQA methods, we include: PSNR [18], NQM [10], UQI [48], SSIM [49], MS-SSIM [50], IFC [41], VIF [40], VSNR-FR [7], RFSIM [57], GSM [30], SRSIM [55], FSIM and FSIMC [58], SFF [8], VSI [56], SCQI [2], LPIPS-Alex and -VGG [60], PieAPP [37], WaDIQaM [5] and DISTS [11].”
MethodAsymmetric Gained Deep Image Compression With Continuous Rate Adaptation
Cui, Z., Wang, J., Gao, S., Guo, T., Feng, Y., & Bai, B. B. (2021) · 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/cvpr46437.2021.01039 · Cited by 233
Setiadi, D. R. I. M., Rustad, S., Andono, P. N., & Shidik, G. F. (2022) · Signal Processing · doi:10.1016/j.sigpro.2022.108908 · Cited by 235
DocUNet: Document Image Unwarping via a Stacked U-Net
Ma, K., Shu, Z., Bai, X., Wang, J., & Samaras, D. (2018) · 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/cvpr.2018.00494 · Cited by 203
“Further replacing a stacked U-Net with a single U-Net decreases MS-SSIM to 0.35 and increases LD to 15.73.”
MethodInfluentialCDDM: Channel Denoising Diffusion Models for Wireless Semantic Communications
Wu, T., Chen, Z., He, D., Qian, L., Xu, Y., Tao, M., & Zhang, W. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3379244 · Cited by 224
“…shown great performance surpassing classic separation-based JPEG2000 source coding and advanced low-density parity-check (LDPC) channel coding, especially for small size images and under human visual perception evaluation matric such as muti-scale structure similarity index measure (MSSSIM) [39].”
BackgroundAtmospheric Turbulence Mitigation Using Complex Wavelet-Based Fusion
Anantrasirichai, N., Achim, A., Kingsbury, N. G., & Bull, D. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2249078 · Cited by 180
A New Color Image Database TID2013: Innovations and Results
Ponomarenko, N., Ieremeiev, O., Lukin, V., Jin, L.-N., Egiazarian, K., Astola, J., Vozel, B., Chehdi, K., Carli, M., Battisti, F., et al. (2013) · Advanced Concepts for Intelligent Vision Systems Conference · doi:10.1007/978-3-319-02895-8_36 · Cited by 106
A Quality-of-Experience Database for Adaptive Video Streaming
Duanmu, Z., Rehman, A., & Wang, Z. (2018) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2018.2822870 · Cited by 155
“In this regard, we evaluate a wide variety of VQA algorithms including PSNR, SSIM [45], MS-SSIM [46], STRRED [49], VQM [48], VMAF [50], SSIMplus [47], and VIIDEO [51] against human subjective scores on two datasets to test their generalizability on streaming videos, where dataset DA includes the videos without stallin…”
MethodSelf-citation360-Degree Textures of People in Clothing from a Single Image
Lazova, V., Insafutdinov, E., & Pons‐Moll, G. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00076 · Cited by 160
“where MSSIM is a Multiscale Structural Similarity index [69, 70], a structural similarity computed at 5 different scales.”
MethodTan, Z., Gao, M., Li, X., & Jiang, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3050551 · Cited by 155
“It can be computed using the multiscale structural similarity (MS-SSIM) [43] to guarantee a satisfactory visual effect, denoted as (10), where l i ( x , y ) , l i ( x , y ) , and l i ( x , y ) are the quantified luminance, contrast, and structure of the image pairs at the i th scale, respectively,…”
MethodMPEG Immersive Video Coding Standard
Boyce, J. M., Doré, R., Dziembowski, A., Fleureau, J., Jung, J., Kroon, B., Salahieh, B., Vadakital, V. K. M., & Yu, L. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3062590 · Cited by 172
HLU2-Net: A Residual U-Structure Embedded U-Net With Hybrid Loss for Tire Defect Inspection
Zheng, Z., Yang, H., Zhou, L., Yu, B., & Zhang, Y. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3126847 · Cited by 150
DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding
Tung, T.-Y., Kurka, D. B., Jankowski, M., & Gündüz, D. (2022) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2022.3231042 · Cited by 194
Wang, X., Ding, J., & Pei, Q. (2015) · Information Sciences · doi:10.1016/j.ins.2015.03.022 · Cited by 144
Learning for Video Compression
Chen, Z., He, T., Jin, X., & Wu, F. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2892608 · Cited by 149
“[4], we also adopt Multi-Scale Structural Similarity (MS-SSIM) [47] as a perceptual metric.”
MethodA perceptual metric for stereoscopic image quality assessment based on the binocular energy
Bensalma, R., & Larabi, M. (2012) · Multidimensional Systems and Signal Processing · doi:10.1007/s11045-012-0178-3 · Cited by 144
Zhou, X., Shen, K., Liu, Z., Gong, C., Zhang, J., & Yan, C. C. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3091312 · Cited by 168
“2, we introduce the hybrid loss [44], which is defined as where l ssim , l bce , and l iou refer to SSIM loss [65], BCE loss [66], and IoU loss [67], respectively.”
BackgroundZhang, W., Qu, C., Ma, L., Guan, J., & Huang, R. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.01.034 · Cited by 143
“Some well-known 2D quality metrics such as C4 [31] and SSIM [32] are used to produce the quality score for stereoscopic images.”
BackgroundMethodInfluentialRe-IQA: Unsupervised Learning for Image Quality Assessment in the Wild
Saha, A., Mishra, S., & Bovik, A. C. (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/cvpr52729.2023.00566 · Cited by 262
“Therefore, during the training phase of the Re-IQA model we use all images in a database both at original and half-scale, thereby doubling the training dataset.”
MethodSelf-citationDense Attention-Guided Cascaded Network for Salient Object Detection of Strip Steel Surface Defects
Zhou, X., Fang, H., Liu, Z., Zheng, B., Sun, Y., Zhang, J., & Yan, C. C. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3132082 · Cited by 180
“where l B i , l I i , and l S i denote binary cross entropy (BCE) loss [77], intersection-over-union (IoU) loss [78], and structural similarity (SSIM) loss [79], respectively.”
BackgroundInfluentialRSGAN: face swapping and editing using face and hair representation in latent spaces
Natsume, R., Yatagawa, T., & Morishima, S. (2018) · ACM SIGGRAPH 2018 Posters · doi:10.1145/3230744.3230818 · Cited by 140
“The consistency of face swapping is evaluated by measuring the absolute difference and multi-scale structural similarity (MS-SSIM) [22] between a input image and a resulting image obtained by swapping faces twice between two input images.”
BackgroundMethodInfluentialLiu, Y., Gu, K., Zhang, Y., Li, X., Zhai, G., Zhao, D., & Gao, W. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2900472 · Cited by 156
Zhao, Y., Li, P., Gao, C., Liu, Y., Chen, Q., Yang, F., & Meng, D. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106338 · Cited by 154
NeRFReN: Neural Radiance Fields with Reflections
Guo, Y.-C., Kang, D., Bao, L., He, Y. H., & Zhang, S. (2022) · 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/cvpr52688.2022.01786 · Cited by 163
“We compare NeRFReN with NeRF and NeRF+D on our RFFR test set using three metrics: PSNR, SSIM [26] and LPIPS [32] (see Tab.”
MethodInfluentialImage Super-Resolution Using Deep Convolutional NetworksPreprint
Dong, C., Loy, C. C., He, K., et al. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1501.00092 · Cited by 140
“Following [42], super-resolution is only applied on the luminance channel (Y channel in YCbCr color space) in Sections 4.1- 4.4, so c = 1 in the first/last layer, and performance (e.g., PSNR and SSIM) is evaluated on the Y channel.”
MethodInfluentialQuaternion Structural Similarity: A New Quality Index for Color Images
Kolaman, A., & Yadid-Pecht, O. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2181522 · Cited by 138
“Structural SIMilarity (SSIM) [16] is a widely used VQM 2 that has many versions, including a scaling version [17], a wavelet version [18], and a perceptual version [19].”
MethodDeep learning-enhanced light-field imaging with continuous validation
Wagner, N., Beuttenmueller, F., Norlin, N., Gierten, J., Boffi, J. C., Wittbrodt, J., WEIGERT, M. G., Hufnagel, L., Prevedel, R., & Kreshuk, A. (2021) · Nature Methods · doi:10.1038/s41592-021-01136-0 · Cited by 152
Wang, Z., & Simoncelli, E. P. (2008) · Journal of Vision · doi:10.1167/8.12.8 · Cited by 138
“A similar concept has also been used in the context of perceptual image quality assessment for qualitatively demonstrating performance (Teo & Heeger, 1994; Wang & Bovik, 2002; Wang et al., 2004) and calibrating parameter settings (Wang et al., 2003).”
MethodSelf-citationMIPGAN—Generating Strong and High Quality Morphing Attacks Using Identity Prior Driven GAN
Zhang, H., Venkatesh, S. K., Ramachandra, R., Raja, K. B., Damer, N., & Busch, C. (2021) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2021.3072349 · Cited by 182
“As suggested in [45], we also set ↵ j = � j = � j , Jj =1 � j = 1 and use the resulting parameters Thus, the proposed loss function can be formulated as: where � 1 , � 2 , � 3 and � 4 are the hyper-parameters that are set to achieve both stable and generalised convergence.”
MethodImage Quality Assessment Using Human Visual DOG Model Fused With Random Forest
Pei, S.-C., & Chen, L.-H. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2440172 · Cited by 132
Quality Assessment Considering Viewing Distance and Image Resolution
Gu, K., Liu, M., Zhai, G., Yang, X., & Zhang, W. (2015) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2015.2459851 · Cited by 135
HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
Yang, L., Wang, S., Ma, S., Gao, W., Liu, C., Wang, P., & Ren, P. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413965 · Cited by 171
“l-world applications, the evaluation criterion for face renovation should be more consistent with human perception rather than machine judgement. Therefore, besides commonly-adopted PSNR and SSIM [56][57] metrics, the evaluation criterion for FR should also reflect the semantic fidelity and perceptual realism of renov…”
MethodAn Adaptive Intelligence Algorithm for Undersampled Knee MRI Reconstruction
Pezzotti, N., Yousefi, S., Elmahdy, M. S., Gemert, J. H. F. V., Schülke, C., Doneva, M., Tolker‐Nielsen, T., Kastryulin, S., Lelieveldt, B. P. F., van Osch, M. J. P., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3034287 · Cited by 170
“Results showed that the linear summation of MSSIM and (cid:96) 1 performed best.”
MethodInfluentialSingle infrared image enhancement using a deep convolutional neural network
Kuang, X., Sui, X., Liu, Y., Chen, Q., & Gu, G. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.11.081 · Cited by 148
Learned hardware-in-the-loop phase retrieval for holographic near-eye displays
Chakravarthula, P., Tseng, E., Srivastava, T., Fuchs, H., & Heide, F. (2020) · ACM Transactions on Graphics · doi:10.1145/3414685.3417846 · Cited by 146
“…1) the learned perceptual image similarity metric (LPIPS) [Zhang et al. 2018] as a deep neural network perceptual quality metric based on human judgments, 2) multi-scale structual similarity index (MSSSIM) [Wang et al. 2003] as a perceptual quality metric, 3) L2 loss for pixel-wise accuracy.”
BackgroundTowards a Quality Metric for Dense Light Fields
Adhikarla, V. K., Vinkler, M., Sumin, D., Mantiuk, R., Myszkowski, K., Seidel, H., & Didyk, P. (2017) · 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/cvpr.2017.396 · Cited by 132
“We also considered a multi-scale version of SSIM2D– MS-SSIM [41] which extends SSIM2D to compute differences on multiple levels.”
MethodA Comprehensive Performance Evaluation of Image Quality Assessment Algorithms
Athar, S., & Wang, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2943319 · Cited by 150
“estimated to be six for the TID2008 database [4] while using the SFMS algorithm, and the following methods are selected: FSIM [83], VIF [100], IFC [86], MAD [6], PSNR-HVS [92], and MSSSIM [89].”
MethodInfluentialSelf-citation
Metadata
- Authors
- Wang, Z., Simoncelli, E. P., & Bovik, A. C.
- Affiliations
- Courant Institute of Mathematical Sciences (US)
- The University of Texas at Austin (US)
- Venue
- The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003
- Publisher
- IEEE
- Published
- 2004-07-08
- Pages
- 1398-1402
- ISSN
- 1058-6393 (ISSN-L)
- OpenAlex
- W1580389772
- Cited by
- 6,253
- References
- 15
- Citations by year
- 2026: 344 · 2025: 675 · 2024: 729 · 2023: 668 · 2022: 662 · 2021: 641 · 2020: 563 · 2019: 438 · 2018: 305 · 2017: 267 · 2016: 206 · 2015: 173 · 2014: 166 · 2013: 112 · 2012: 89
- FWCI
- 3.98
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Asilomar Conference on Signals, Systems and Computers (ACSSC) (publishedVersion)
- 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
- structural similarity, image quality assessment, multiscale analysis, human visual system, perceptual image quality, image generation, parameter calibration, viewing conditions
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.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
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.