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 1,101–1,200 of 6,047
AI in Video Analysis, Production and Streaming Delivery
Jayanthiladevi, A., Raj, A. G., Narmadha, R., et al. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1712/1/012014 · Cited by 34
“It uses pixel to pixel comparison which does not replicate the insight of recipient [3].”
BackgroundDeep learning-based video stream reconstruction in mass-production diffractive optical systems
EVDOKIMOVA, V. V., RAS, I. R. –. B. O. T. F. “. A. P., Petrov, M. V., et al. (2021) · Computer Optics · doi:10.18287/2412-6179-co-834 · Cited by 34
“Оценка качества реконструкции при использовании разных функций потерь Функция потерь PSNR для линзы с показателем гармоничности 13 PSNR для линзы с показателем гармоничности 7 l1 24,67 26,54 l2 27,02 26,44 SSIM [6] 25,6 24,94 MS-SSIM [6] 25,9 25,03 Комбинация MS-SSIM и l1 26,28 26,57 Комбинация MS-SSIM и l2 26,37 26,5…”
InfluentialMR-contrast-aware image-to-image translations with generative adversarial networks
Denck, J., Guehring, J., Maier, A., & Rothgang, E. M. (2021) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-021-02433-x · Cited by 39
“The MS-SSIM is a measure of structural similarity over several scales allowing to incorporate image details at different resolutions [15].”
MethodHua, L., Yu, M., He, Z., et al. (2021) · IET Image Processing · doi:10.1049/ipr2.12211 · Cited by 33
“Many classical IQA metrics were presented, such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM) [6], Multiscale Structural SIMilarity (MS-SSIM) [7] and Visual Information Fidelity in Pixel domain (VIFP) [8].”
MethodLatent-Space Scalability for Multi-Task Collaborative Intelligence
Choi, H., & Bajić, I. V. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506712 · Cited by 49
“Distortion D is computed as where α and β are scale factors used to achieve various trade-offs, MSE is the mean squared error, and MS-SSIM is the multi-scale structural similarity index metric [25].”
MethodDeep Learning-based Distortion Sensitivity Prediction for Full-Reference Image Quality Assessment
Ahn, S., Choi, Y., & Yoon, K. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00044 · Cited by 42
“We compared the proposed model against FR-IQA models (PSNR [1], NQM [6], UQI [43], SSIM [44], MS-SSIM [45], IFC [38], VIF [37], VSNR [4], RFSIM [49], GSM [27], SRSIM [47], FSIM [50], FSIMc [50], VSI [48], MAD [23], LPIPS-Alex [51], LPIPS-VGG [51], PieAPP [33], WaDIQaM [3], DISTS [8], SWD [11], and DeepQA [19]) and NR-…”
MethodDPICT: Deep Progressive Image Compression Using Trit-Planes
Lee, J.-H., Jeon, S., Choi, K. P., Park, Y., & Kim, C. (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/cvpr52688.2022.01564 · Cited by 62
“We measure the rate by bits per pixel (bpp), and the distortion by peakto-signal ratio (PSNR) and multi-scale structural similarity (MS-SSIM) [45].”
MethodInfluentialContrast stretching based pansharpening by using weighted differential evolution algorithm
Çivicioğlu, P., & Beşdok, E. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118144 · Cited by 34
SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment
Liu, J., Li, X., Peng, Y., Yu, T., & Chen, Z. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00194 · Cited by 36
Edge-Computing-Facilitated Nighttime Vehicle Detection Investigations With CLAHE-Enhanced Images
Lashkov, I., Yuan, R., & Zhang, G. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3255202 · Cited by 36
“• MS-SSIM [48] expands on the SSIM index by combining luminance information at the highest resolution level with structure and contrast information at several down sampled resolutions, or scales.”
BackgroundPassive superresolution imaging of incoherent objects
Frank, J., Duplinskiy, A., Bearne, K., & Lvovsky, A. I. (2023) · Optica · doi:10.1364/optica.493718 · Cited by 50
“2 We quantify the image quality with respect to the ground truth objects by computing multi-scale structural similarity (MS-SSIM) [28] [Fig.”
Motion Information Propagation for Neural Video Compression
Qi, L., Li, J., Li, B., Li, H., & Lu, Y. (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/cvpr52729.2023.00592 · Cited by 37
“d(·) refers to mean square error (MSE) when targeted at PSNR or 1 MS-SSIM [40] when targeted at SSIM.”
BackgroundInfluentialApplying Collaborative Adversarial Learning to Blind Point Cloud Quality Measurement
Wang, J., Gao, W., & Li, G. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3322475 · Cited by 55
“It has been shown that multiscale features have a strong correlation with HVS and thus can improve the model performance on quality measurement tasks, such as MS-SSIM metric [47] in IQA and MS-GraphSIM metric [37] in PCQM.”
BackgroundMethodPixel-level clustering network for unsupervised image segmentation
Hoang, C. M., & Kang, B. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107327 · Cited by 42
“L ms - ssim ( I , ˆ I ) is computed as follows: where MS-SSIM is computed by the method in (Wang et al., 2003, 2004).”
MethodChang, C., Peng, J., Safari, M., Salari, E., Pan, S., Roper, J. R., Qiu, R. L. J., Gao, Y., Shu, H. G., Mao, H. Z., et al. (2024) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad209c · Cited by 58
Dynamic Hypergraph Convolutional Network for No-Reference Point Cloud Quality Assessment
Chen, W., Jiang, Q., Zhou, W., Xu, L., & Lin, W. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3410052 · Cited by 42
“As a result, existing IQA methods can be used, including SSIM [62], MS-SSIM [63], IW-SSIM [64], VIFP [65], and more.”
BackgroundMethodAdaptive psychometric scaling for video quality assessment
Menkovski, V., & Liotta, A. (2012) · Signal Processing Image Communication · doi:10.1016/j.image.2012.01.004 · Cited by 34
“Some effective FR methods include MultiScale-Structural SIMilarity index (MS-SSIM) [5], Video Quality Metric (VQM) [6], Perceptual Video Quality Metric (PVQM) [7], and the perceptual spatio-temporal frequency-domain MOtion-based Video Integrity Evaluation (MOVIE) [8].”
MethodKazakevičiūtė, A., Ho, C. J. H., & Olivo, M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2550624 · Cited by 33
Imaging through plasmonic nanoparticles
Tanzid, M., Sobhani, A., DeSantis, C. J., Cui, Y., Hogan, N. J., Samaniego, A. P., Veeraraghavan, A., & Halas, N. J. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1603536113 · Cited by 33
A Study on Quality Metrics for 360 Video Communications
Tran, H. T. T., PHAM, C. T., Ngoc, N. P., Pham, A. T., & Thang, T. C. (2017) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2017mup0011 · Cited by 33
Video quality assessment accounting for temporal visual masking of local flicker
Choi, L. K., & Bovik, A. C. (2018) · Signal Processing: Image Communication · doi:10.1016/j.image.2018.06.009 · Cited by 33
“For example, the first symbol value of ‘1’ at the second row and at the first column in Table 3 means that MS-SSIM is statistically better than PSNR on the LIVE VQA database.”
MethodInfluentialSelf-citationRobust and Unobtrusive Display-to-Camera Communications via Blue Channel Embedding
Chen, C., Huang, W., Zhang, L., et al. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2865681 · Cited by 33
“However, the multi-scale structural similarity (MS-SSIM) metric [29] has been adopted in our prior works [9], [10] and in this work.”
End-to-End Learning of Video Compression using Spatio-Temporal Autoencoders
Pessoa, J., Aidos, H., Tomás, P., et al. (2020) · SiPS ... design and implementation - IEEE Workshop on Signal Processing Systems · doi:10.1109/sips50750.2020.9195249 · Cited by 33
“5(B) for the RGB color space (for which the network was optimized), including both MS-SSIM and PSNR metrics as a per-frame average.”
BackgroundMethodInfluentialKofler, A., Haltmeier, M., Schaeffter, T., & Kolbitsch, C. (2021) · Medical Physics · doi:10.1002/mp.14809 · Cited by 34
LC-GAN: Image-to-image Translation Based on Generative Adversarial Network for Endoscopic Images
Lin, S., Qin, F., Li, Y., Bly, R. A., Moe, K. S., & Hannaford, B. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341556 · Cited by 51
“Similar to [36], [37], we propose a multi-scale method that compares the image structural information at different resolutions.”
MethodSelf-Conditioned Probabilistic Learning of Video Rescaling
Tian, Y., Lu, G. S., Min, X., Che, Z., Zhai, G., Guo, G., & Gao, Z. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00445 · Cited by 41
“3, our method saves the bit cost or the storage space by over 30% averagely under the same MS-SSIM, compared with the vanilla H.265 codec.”
MethodInfluentialDeep Dehazing Network for Remote Sensing Image with Non-Uniform Haze
Jiang, B., Chen, G., Wang, J., et al. (2021) · Remote Sensing · doi:10.3390/rs13214443 · Cited by 33
“We use MS-SSIM [24], an SSIM loss function based on multiple layers (e.”
MethodInfluentialMultiple hypothesis colorization and its application to image compression
Baig, M. H., & Torresani, L. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.01.010 · Cited by 33
E-LPIPS: Robust Perceptual Image Similarity via Random Transformation EnsemblesPreprint
Kettunen, M., Härkönen, E., & Lehtinen, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.03973 · Cited by 95
“Perceptually motivated image similarity metrics have a long history, with well-known challenges due to dependence on context and high-level image structure [27, 28, 20].”
BackgroundInfrared and visible image fusion via octave Gaussian pyramid framework
Yan, L., Hao, Q., Cao, J., et al. (2021) · Scientific Reports · doi:10.1038/s41598-020-80189-1 · Cited by 32
Learned Video Compression With Efficient Temporal Context Learning
Jin, D., Lei, J., Peng, B., Pan, Z., Li, L., & Ling, N. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3276333 · Cited by 42
“D ( x t , ˆ x t ) denotes the reconstruction distortion measured by mean square error (MSE) or negative multiscale structural similarity (MS-SSIM) [43].”
MethodMI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices
Sargsyan, A., Navasardyan, S., Xu, X., & Shi, H. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00674 · Cited by 74
“Additionally, in order to further prove the robustness of our approach against other metrics, we also include a comparison in terms of PSNR, SSIM [55], P-IDS and U-IDS [65] metrics in the appendix.”
MethodChen, R., Zhang, W., Song, F., Yu, H., Cao, D., Zheng, Y., He, M., & Shi, D. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01018-7 · Cited by 57
Review of Deep Learning-Based Image Inpainting Techniques
Yang, J., & Ruhaiyem, N. I. R. (2024) · IEEE Access · doi:10.1109/access.2024.3461782 · Cited by 48
“When they equal 1, the SSIM is shown following : [155] is an advanced version of the SSIM.”
MethodMLIC ++ : Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression
Jiang, W., Yang, J., Zhai, Y., Gao, F., & Wang, R. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3719011 · Cited by 110
“In latent representation ˆ 𝒚 ∈ R 𝐿 × 𝐶 , where 𝐿 = 𝐻 × 𝑊 , C is the channel number, each channel contains distinct information, but they can be considered as thumbnails, as depicted in Figure 2.”
Attention modeling for video quality assessment: Balancing global quality and local quality
You, J., Korhonen, J., & Perkis, A. (2010) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2010.5583037 · Cited by 32
Face Detection on Distorted Images Augmented by Perceptual Quality-Aware Features
Gunasekar, S., Ghosh, J., & Bovik, A. C. (2014) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2014.2360579 · Cited by 35
“Substantial research efforts have recently focused on the development of automated image quality algorithms (IQA) that aim to accurately predict end–user quality–of–experience.”
BackgroundSelf-citationEvaluation of 60 full-reference image quality metrics on the CID:IQ
Pedersen, M. (2015) · International Conference on Information Photonics · doi:10.1109/icip.2015.7351068 · Cited by 33
Reduced-reference image quality assessment based on distortion families of local perceived sharpness
Zhang, Y., Phan, T. D., & Chandler, D. M. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.03.020 · Cited by 31
Gradient magnitude similarity deviation on multiple scales for color image quality assessment
Zhang, B., Sander, P. V., & Bermak, A. (2017) · IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.2017.7952357 · Cited by 32
“Multiscaled GMSD The subjective assessment of image quality may vary depending on observing distance and a good IQA index should be able to assess the image quality at different scales [8].”
BackgroundMethodInfluentialLayered Image Compression Using Scalable Auto-Encoder
Jia, C., Liu, Z., Wang, Y., Ma, S., & Gao, W. (2019) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2019.00087 · Cited by 30
VORNet: Spatio-Temporally Consistent Video Inpainting for Object Removal
Chang, Y.-L., Liu, Z. Y., & Hsu, W. H. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00229 · Cited by 43
“We train our VORNet on the SVOR dataset with reconstruction loss, perceptual loss and two designed GAN losses and evaluate the quality of videos with mean square error, SSIM [37], a learned perceptual metric [51] and visual results.”
MethodShi, C.-Y., & Lin, Y.-D. (2020) · IEEE Access · doi:10.1109/access.2020.2995420 · Cited by 23
Zhou, X., Zhang, Y., Li, N., Wang, X., Zhou, Y., & Ho, Y. (2021) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2021.3056231 · Cited by 37
“SSIM is a milestone for connecting the objective image quality with the Human Vision System (HVS), its variants [4], [5] further improve the quality prediction accuracy in most databases.”
BackgroundLearning Semantic-Aware Dynamics for Video Prediction
Bei, X., Yang, Y., & Soatto, S. (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/cvpr46437.2021.00096 · Cited by 49
“Higher MS-SSIM scores and lower LPIPS distances suggest better performance.”
MethodInfluentialBilevel Methods for Image Reconstruction
Crockett, C., & Fessler, J. A. (2022) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000111 · Cited by 55
“A multiscale extension of SSIM, called MS-SSIM, considers information at different resolutions [71].”
MethodIris Image Compression Using Deep Convolutional Neural Networks
Jalilian, E., Hofbauer, H., & Uhl, A. (2022) · Sensors · doi:10.3390/s22072698 · Cited by 32
“The luminescence comparison is computed only at scale M, and the final MS-SSIM evaluation is obtained by combining the measurements at different scales [39].”
MethodCao, Y., Wan, Z., Ren, D., Yan, Z., & Zuo, W. (2022) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr52688.2022.00576 · Cited by 36
“B, we take an example image from validation set of PIPAL to visually show the consistency be-tween various methods and subjective perception, inlcuding PSNR, SSIM [58], MS-SSIM [61], LPIPS [73], IQT [9] and our method.”
MethodInfluentialAn Introduction to Neural Data Compression
Yang, Y., Mandt, S., & Theis, L. (2023) · doi:10.1561/9781638281757 · Cited by 35
MDVSC—Wireless Model Division Video Semantic Communication for 6G
Bao, Z., Liang, H., Dong, C., Xu, X., & Liu, G. (2023) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps58843.2023.10464666 · Cited by 33
“The MDVSC is trained in terms of the mean square error (MSE) and tested under the PSNR, or MS-SSIM [11] for perceptual quality.”
MethodRange image quality assessment by Structural Similarity
Malpica, W., & Bovik, A. C. (2009) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2009.4959792 · Cited by 32
Self-citationTowards Benchmarking Scene Background InitializationPreprint
Maddalena, L., & Petrosino, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.04051 · Cited by 32
“7) MultiScale Structural Similarity Index (MS-SSIM): This is the metric defined in [4], that uses structural”
MethodDeepFL-IQA: Weak Supervision for Deep IQA Feature LearningPreprint
Lin, H., Hosu, V., & Saupe, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.08113 · Cited by 81
“These methods are SSIM [2], MS-SSIM [20], IW-SSIM [21], MDSI [29], VSI [24], FSIMc [22], GMSD [26], SFF [25], SCQI [27], ADD-GSIM [28], and SR-SIM [23].”
MethodPeCo: Perceptual Codebook for BERT Pre-training of Vision TransformersPreprint
Dong, X., Bao, J., Zhang, T., Chen, D., Zhang, W., Yuan, L., Chen, D., Wen, F., Yu, N., & Guo, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12710 · Cited by 32
“Numerous efforts have been proposed to achieve that, such as SSIM [67], MSSIM [68], FSIM [71], and HDR-VDP [47].”
MethodTu, Z., Lin, J., Wang, Y., Adsumilli, B., & Bovik, A. C. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.3024985 · Cited by 31
“However, it has been shown that traditional video quality metrics like PSNR and even SSIM family [31]–[33] do not align very well with human perception of banding [19].”
BackgroundSelf-citationChen, E., Guo, M., Tian, Y., Zhang, Y., Chen, H., Le, J., Zhong, F., & Zhang, H. (2023) · Physics of Fluids · doi:10.1063/5.0140624 · Cited by 33
CLEGAN: Toward Low-Light Image Enhancement for UAVs via Self-Similarity Exploitation
Xing, L., Qu, H., Xu, S., & Tian, Y. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3279826 · Cited by 42
“…the differences in color, structure, and high-level feature similarity, we adopt mean absolute error (MAE), peak signal-to-noise ratio (PSNR) [49], structural similarity (SSIM) [50], and learned perceptual image patch similarity metric (LPIPS) [51] as evaluation metrics, which are employed…”
MethodSrivastava, D., Singh, S. S., Rajitha, B., Verma, M., Kaur, M., & Lee, H.-N. (2023) · IEEE Access · doi:10.1109/access.2023.3308911 · Cited by 49
“Several articles, including [118], [119], [120], [121], [122], discussed various approaches employed for the extraction of image texture components.”
BackgroundCoarse-to-Fine Low-Light Image Enhancement With Light Restoration and Color Refinement
Wu, X. D., Lai, Z., Yu, S., Zhou, J., Liang, Z., & Shen, L. (2023) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2023.3314436 · Cited by 34
“AstheMS-SSIM[47] isbasedonthedegradationofimagestructureinformationand referencedthehumanvisualsystem,thevisuallossisbuiltby theMS-SSIM.”
MTDFusion: A Multilayer Triple Dense Network for Infrared and Visible Image Fusion
Karim, S., Tong, G., Li, J., et al. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3329148 · Cited by 31
“We have completed quantitative assessments using multiple representative evaluation metrics such as Q ab / f [54], Q G [55], FMI w [56], QMI [57], [58], Q Y [59], nonlinear correlation information entropy (QNCIE) [60], MI2 [61], Q P [62], Q CV [63], and MS-SSIM [64].”
MethodKoyuncu, A. B., Jia, P., Boev, A., Alshina, E. A., & Steinbach, E. G. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3371686 · Cited by 42
“· To evaluate the perceptual quality of our models, we finetuned them with MS-SSIM [54] as the distortion metric for ∼ 500K iterations.”
MethodInfluentialMeta-Processing: A robust framework for multi-tasks seismic processing
Cheng, S., Harsuko, R., & Alkhalifah, T. A. (2024) · Surveys in Geophysics · doi:10.1007/s10712-024-09837-9 · Cited by 43
“[65], we set five scales, and the exponents are β1 = γ1 = 0.”
Hoffman, D. M., & Stolitzka, D. (2014) · Journal of the Society for Information Display · doi:10.1002/jsid.297 · Cited by 30
“8 11 Others have been trained using large data sets of impaired images.”
BackgroundFeature maps driven no-reference image quality prediction of authentically distorted images
Ghadiyaram, D., & Bovik, A. C. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2084807 · Cited by 36
“91 MS-SSIM [32] 0.”
Self-citationSelf-adaptive scale transform for IQA metric
Gu, K., Zhai, G., Yang, X., & Zhang, W. (2013) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2013.6572353 · Cited by 35
Screen content image quality assessment using edge model
Ni, Z.-K., Ma, L., Zeng, H., Cai, C., & Ma, K.-K. (2016) · International Conference on Information Photonics · doi:10.1109/icip.2016.7532323 · Cited by 31
Geng, X., Shen, L., Li, K., & An, P. (2016) · Signal Processing Image Communication · doi:10.1016/j.image.2016.12.004 · Cited by 33
“Finally, 2D-IQA metrics, such as PSNR [56], SSIM [1], MS-SSIM [57] and VIF [58] are computed on the synthesized cyclopean images to represent the quality of stereoscopic image.”
MethodLöhdefink, J., Bär, A., Schmidt, N. M., Hüger, F., Schlicht, P., & Fingscheidt, T. (2019) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2019.8813813 · Cited by 39
Detail-Preserving CycleGAN-AdaIN Framework for Image-to-Ink Painting Translation
Zhang, F., Gao, H., & Lai, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3009470 · Cited by 33
Fast and slow curiosity for high-level exploration in reinforcement learning
Bougie, N., & Ichise, R. (2020) · Applied Intelligence · doi:10.1007/s10489-020-01849-3 · Cited by 37
“While l 2 ignores the intricate characteristics of the human visual system, MS-SSIM is sensitive to changes in local structures and performs well on real-world images with different scales.”
BackgroundInfluentialActive Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment
Wang, Z., & Ma, K. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3071759 · Cited by 51
“In addition to testing the model generalizability using [19] and deepIQA [18], when competing with a full-reference IQA method, MS-SSIM [28], in the gMAD competition on the Waterloo Exploration Database [29]. gMAD, here we shift our attention to leveraging gMAD examples to improve the BIQA…”
MethodSelf-citationApplication of a Radar Echo Extrapolation‐Based Deep Learning Method in Strong Convection Nowcasting
Yin, J., Gao, Z., & Han, W. (2021) · Earth and Space Science · doi:10.1029/2020ea001621 · Cited by 37
“MS-SSIM is a comprehensive evaluation metric that is, obtained by iteratively calculating the SSIM of different resolutions (scales; Wang et al., 2003):”
MethodOcclusion-aware Bi-directional Guided Network for Light Field Salient Object Detection
Dong, J., Zhang, S., Cong, R., & Lin, Y. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475312 · Cited by 48
“BASNet proposes a novel hybrid loss that fuses BCE, SSIM and IoU to supervise the training process of accurate SOD on three levels: pixel-level, patch-level and map-level.”
MethodNeural Distributed Image Compression Using Common Information
Mital, N., Özyılkan, E., Garjani, A., & Gündüz, D. (2022) · DCC · doi:10.1109/dcc52660.2022.00026 · Cited by 32
“The MS-SSIM has been widely reported to provide a better measure of human perception of distortion [21].”
MethodTowards a More Realistic and Detailed Deep-Learning-Based Radar Echo Extrapolation Method
Hu, Y., Chen, L., Wang, Z., Pan, X., & Li, H. (2021) · Remote Sensing · doi:10.3390/rs14010024 · Cited by 31
Self-citationTR-GAN: Multi-Session Future MRI Prediction With Temporal Recurrent Generative Adversarial Network
Fan, C.-C., Peng, L., Wang, T., Yang, H., Zhou, X.-H., Ni, Z.-L., Wang, G., Chen, S., Zhou, Y.-J., & Hou, Z.-G. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3151118 · Cited by 42
“In the MSL module, the number of randomly cropped patches Three image metrics: MSE, multi-scale structural similarity metric (MS-SSIM) [45], and peak signal to noise ratio (PSNR) are adopted to evaluate the authenticity of the generated MRI results.”
RestainNet: A self-supervised digital re-stainer for stain normalization
Zhao, B., Han, C., Pan, X., Lin, J., Yi, Z., Liang, C., Chen, X., Li, B., Qiu, W., Li, D., et al. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108304 · Cited by 44
“Erreur Relative Globale Adimensionnelle de Synthèse (ERGAS),Universal Quality Index (UQI) [11], Structural Similarity Index (SSIM) [10], Mean Squared Error (MSE),Relative Average Spectral Error (RASE), Root Mean Square Error (RMSE) [8], Multi-scale Structural Similarity Index (MSSSIM) [9].”
BackgroundA Multiscale Approach to Deep Blind Image Quality Assessment
Liu, M., Huang, J., Zeng, D., Ding, X., & Paisley, J. W. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3245991 · Cited by 43
“Subsequently, the structural similarity index (SSIM [9]), multiscale SSIM (MS-SSIM [10]) and information weighted SSIM (IW-SSIM [11]), were proposed to evaluate image quality by measuring the structural information, along with the luminance and contrast information.”
MethodDCFusion: A Dual-Frequency Cross-Enhanced Fusion Network for Infrared and Visible Image Fusion
Wu, D., Han, M., Yang, Y., Zhao, S., Rao, Y., Li, H., Xing, L., Zhou, C., & Bai, H. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3267380 · Cited by 50
TriPlaneNet: An Encoder for EG3D Inversion
Bhattarai, A. R., Nießner, M., & Sevastopolsky, A. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00303 · Cited by 52
Quality index evaluation of videos based on fuzzy interface system
Al‐Naji, A., Lee, S., & Chahl, J. (2017) · IET Image Processing · doi:10.1049/iet-ipr.2016.0569 · Cited by 35
Subjective Quality Assessment of Stereoscopic Omnidirectional Image
Xu, J., Lin, C., Zhou, W., & Chen, Z. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00776-8_54 · Cited by 28
Baker, A., Hammerling, D., & Turton, T. L. (2019) · Computer graphics forum (Print) · doi:10.1111/cgf.13707 · Cited by 36
Perceptual Quality Study on Deep Learning Based Image Compression
Cheng, Z., Akyazi, P., Sun, H., Katto, J., & Ebrahimi, T. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803824 · Cited by 30
“PSNR or MS-SSIM [16].”
Learning Accurate Entropy Model with Global Reference for Image CompressionPreprint
Qian, Y., Tan, Z., Sun, X., Lin, M., Li, D., Sun, Z., Li, H., & Jin, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.08321 · Cited by 88
“The second term d(x, x̂) represents the distortion value under given metric, such as mean squared error (MSE) or MS-SSIM (Wang et al. [2003]).”
InfluentialNo-Reference Deep Quality Assessment of Compressed Light Field Images
Guo, Z., Gao, W., Wang, H., Wang, J., & Fan, S. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428383 · Cited by 32
“MSE and PSNR predict image quality according to the signal confi-dence, SSIM [4] and MS-SSIM [5] predicts the quality according to the structural similarity and transformation of the image.”
MethodUsing diffusion models to generate synthetic labeled data for medical image segmentation
Saragih, D., Hibi, A., & Tyrrell, P. N. (2024) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-024-03213-z · Cited by 46
“For our implementation of the diffusion model, our sampling number is set to be T = 200, but we skipped the first 80 timesteps.”
MethodConsistNet: Enforcing 3D Consistency for Multi-View Images Diffusion
Yang, J., Cheng, Z., Duan, Y., Ji, P., & Li, H. (2024) · 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/cvpr52733.2024.00676 · Cited by 83
“We report SSIM score [42] and multiscale SSIM score [43], denoted as SSIM and MS-SSIM accordingly.”
BackgroundMethodAlshina, E. A., Ascenso, J., & Ebrahimi, T. (2024) · IEEE Multimedia · doi:10.1109/mmul.2024.3485255 · Cited by 30
Xu, K., Wei, A., Zhang, C., Chen, Z., Lu, K., Hu, W., & Lu, F. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3548202 · Cited by 45
“Finally, the detail-level information constraint module uses the multiscale structural similarity (MS-SSIM) [39] operator to dynamically evaluate the similarity between the fused and source images in terms of luminance, contrast, and structure, improving the performance of the fused image at the…”
Objective Image Quality Assessment: Facing The Real-World Challenges
Wang, Z. (2016) · Electronic Imaging · doi:10.2352/issn.2470-1173.2016.13.iqsp-205 · Cited by 38
Self-citationSparse representation-based image quality assessment
Guha, T., Nezhadarya, E., & Ward, R. (2013) · Signal processing. Image communication · doi:10.1016/j.image.2014.09.010 · Cited by 39
“improve the performance of SSIM, multiscale extension [11], wavelet transform-based modification [14], gradient-domain implementation [12] and various pooling strategies [13], [15]”
BackgroundPyramid Embedded Generative Adversarial Network for Automated Font Generation
Sun, D., Zhang, Q., & Yang, J. J. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545701 · Cited by 35
“dation as perceived change in structural information, and they also incorporates important perceptual phenomena, including both luminance masking and contrast masking terms [22].”
BackgroundSparse Representation-Based Video Quality Assessment for Synthesized 3D Videos
Zhang, Y., Zhang, H., Yu, M., Kwong, S., & Ho, Y. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2929433 · Cited by 29
“Similarly, on CT CD , our proposed method performs the best among them while Liu and IW-SSIM have very similar performance, and MSSSIM and SSIM perform fairly good and are better than other methods.”
InfluentialBlind Image Quality Assessment Based on Multi-scale KLT
Yang, C., Zhang, X., An, P., Shen, L., & Kuo, C. ‐. J. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3001537 · Cited by 31
“As the multi-scale analysis strategy is effective in many IQA approaches[39],[40],weextracttheproposedKLTfeatureswith multiplescalesfromthetestimages.”
MethodBlind Stereoscopic Image Quality Assessment By Deep Neural Network Of Multi-Level Feature Fusion
Yan, J., Fang, Y., Huang, L., Min, X., Yao, Y., & Zhai, G. (2020) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme46284.2020.9102888 · Cited by 32
“Inspired by the multi-scale characteristics [27] and binocular perceptual mechanisms [11, 12, 13], we fuse the feature maps extracted from different layers of the left- and right-view images.”
BackgroundMethodYan, J., Fang, Y., Du, R., Zeng, Y., & Zuo, Y. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3003218 · Cited by 33
“The study [47] demonstrate that multi-scale property exists in the HVS when we perceive the visual information, thus we extract visual features of images with multi-scale for better representation.”
BackgroundImage Coding With Data-Driven Transforms: Methodology, Performance and Potential
Zhang, X., Yang, C., Li, X., Liu, S., Yang, H., Katsavounidis, I. X., Lei, S.-M., & Kuo, C. ‐. J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3025203 · Cited by 30
“Although this method achieved visual quality improvement based on MS-SSIM [40], its compression performance is still inferior according to PSNR quality metric.”
MethodThermoWave: a new paradigm of wireless passive temperature monitoring via mmWave sensing
Chen, B., Li, H., Li, Z., Chen, X., Xu, C., & Xu, W. (2020) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3372224.3419184 · Cited by 35
“Structural Similarity Index:We utilize Structural Similarity Index (SSIM) [51, 52] for the thermal image structural comparison between prediction and ground truth.”
MethodInfluentialA comparative analysis of multi-backbone Mask R-CNN for surgical tools detection
Ciaparrone, G., Bardozzo, F., Priscoli, M. D., Kallewaard, J. L., Zuluaga, M. R., & Tagliaferri, R. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206854 · Cited by 35
“The implemented tracking procedure is based on a two-phase comparison: i) evaluation of the proximity of the bounding boxes, ii) the computation of the structural similarity index (SSIM) [42] between the two frame-adjacent masks.”
Method
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.