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 1,701–1,800 of 6,047
StegGAN: hiding image within image using conditional generative adversarial networks
Singh, B., Sharma, P. K., Huddedar, S. A., Sur, A., & Mitra, P. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13172-9 · Cited by 19
“In addition to traditional evaluation metrics PSNR and SSIM, the StegGAN has also achieved notable results in terms of VIf [45] ∼ 0.87 , 0.66, MS-SSIM [56] ∼ 0.99 , 0.95 and UQI [54] ∼ 0.99 , 0.93 on the pairs (Cover, Stego) and (Secret, Extracted) respectively, as shown in Table 1.”
MethodInfluentialStainCUT: Stain Normalization with Contrastive Learning
Pérez, J. C. G., Baguer, D. O., & Maaß, P. (2022) · Journal of Imaging · doi:10.3390/jimaging8070202 · Cited by 18
“The performance of the methods was evaluated by comparing against the ground truths using four similarity measures: the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM) [27], Feature Similarity Index (FSIM) [28]) and the Learned Perceptual Image Patch Similarity (LPIPS) [29].”
MethodA Decoupled Kernel Prediction Network Guided by Soft Mask for Single Image HDR Reconstruction
Cao, G., Zhou, F., Liu, K., et al. (2022) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3550277 · Cited by 18
“We assess the overall performance in terms of the Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM) [36], Multi-Scale Structural Similarity (MSSSIM) [37], and HDR-VDP-2.”
MethodDeep Controllable Backlight Dimming for HDR Displays
Duan, L., Marnerides, D., Chalmers, A. G., et al. (2022) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2022.3188806 · Cited by 18
“The metrics used for comparison were the Perceptually Uniform (PU) [41] versions of PSNR, Multi-Scale SSIM [42], along with HDR-VDP-2.”
MethodDeep-Learning-Based Gas Leak Source Localization From Sparse Sensor Data
Badawi, D., Bassi, I., Ozev, S., & Çetin, A. E. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3202134 · Cited by 18
“The second term SSIM in (15) refers to the structural similarity index metric [34].”
BackgroundModeling Perceived Quality on 8K VVC Video Under Various Screen Sizes and Viewing Distances
Sugito, Y., Kondo, Y., Arai, D., et al. (2022) · IEEE Access · doi:10.1109/access.2022.3206034 · Cited by 18
Robust Semantic Transmission of Images with Generative Adversarial Networks
He, Q. F., Yuan, H., Feng, D., et al. (2022) · Globecom · doi:10.1109/globecom48099.2022.10000735 · Cited by 18
“is peak signal-to-noise ratio (PSNR) and multi-scale structural similarity (MS-SSIM), to measure the reconstruction quality of images, wherein PSNR evaluates the difference between two images at the pixel level, and MS-SSIM measures the similarity of two images in multi-scale structures [14].”
BackgroundFloLPIPS: A Bespoke Video Quality Metric for Frame Interpolation
Danier, D., Zhang, F., & Bull, D. (2022) · Picture Coding Symposium · doi:10.1109/pcs56426.2022.10018062 · Cited by 56
Image-Consistent Detection of Road Anomalies as Unpredictable Patches
Vojir, T., & Matas, J. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00545 · Cited by 34
“The SSIM is the structural similarity index measure [43].”
MethodA Glaucoma Detection System Based on Generative Adversarial Network and Incremental Learning
Chang, C.-W., Chang, C., Lin, Y.-Y., Su, W.-W., & Chen, H. S.-L. (2023) · Applied Sciences · doi:10.3390/app13042195 · Cited by 19
Jurek, J., Materka, A., Ludwisiak, K., Majos, A., Gorczewski, K., Cepuch, K., & Zawadzka, A. (2023) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2022.12.006 · Cited by 19
Yuan, P., Bai, R., Yan, Y., Li, S.-J., Wang, J., Cao, C., & Wu, Q. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.1118087 · Cited by 9
“The structural similarity (SSIM) Wang et al. (2004) compares three visual aspects including contrast, luminance, and structure.”
BackgroundMethodInfluentialQuality assessment of higher resolution images and videos with remote testing
Göring, S., Rao, R. R. R., & Raake, A. (2023) · Quality and User Experience · doi:10.1007/s41233-023-00055-6 · Cited by 21
“Based on the conducted subjective test, it is possible to evaluate the performance of objective image or video quality metrics, i.e., VMAF [61, 69], ADM2 [57], VIF [101], PSNR, SSIM [112], and MS-SSIM [113].”
BackgroundForty years of color quantization: a modern, algorithmic survey
Celebi, M. E. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10406-6 · Cited by 25
“20 msssim is a variant of ssim computed over a range of scales (Wang et al. 2003).”
BackgroundReading Various Types of Pointer Meters Under Extreme Motion Blur
Zhang, H., Rao, Y., Shao, J., Meng, F., & Pu, J. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3290962 · Cited by 24
“…Quality Evaluation: Peak signal to noise ratio (PSNR) [45], structural similarity index measure (SSIM) [46], universal quality index (UQI) [47], and multiscale structural similarity index measure (MSSIM) [48] are adopted to evaluate the effectiveness of our method in recovering blurred images.”
MethodLight Field Image Quality Assessment Using Natural Scene Statistics and Texture Degradation
Ma, J., Zhang, X., Jin, C., An, P., & Xu, G. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3297016 · Cited by 22
“Over the past decade, traditional 2D/3D IQA methods have been researched extensively and many classic 2D IQA works [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18], [19], [20] have been proposed.”
MethodAn, W., Bao, Z., Liang, H., Dong, C., & Xu, X. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3352737 · Cited by 20
“(28), and the formula for calculating MS-SSIM [26] is as follows: where l ( I m , (cid:99) I m ) , c ( I m , (cid:99) I m ) and s ( I m , (cid:99) I m ) denote luminance, contrast and structure comparison measures, respectively.”
BackgroundQuantum Denoising Diffusion Models
Kölle, M., Stenzel, G., Stein, J., Zielinski, S., Ommer, B., & Linnhoff–Popien, C. (2024) · IEEE International Conference on Quantum Software (QSW) · doi:10.1109/qsw62656.2024.00023 · Cited by 51
“To gauge the quality of our generated images, we employ three metrics: the Fr ´ echet Inception Distance (FID) [16, 27], the Structural Similarity Index Measure (SSIM) [53], and the Peak Signal-to-Noise Ratio (PSNR).”
MethodDiffusion-Driven GAN Inversion for Multi-Modal Face Image Generation
Kim, J., Oh, C., Do, H., Kim, S.-H., & Sohn, K. (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/cvpr52733.2024.00990 · Cited by 38
“Frechet Inception Distance (FID) [17], LPIPS [63], and the Multiscale Structural Similarity (MS-SSIM) [56] are employed for the evaluation of visual quality and diversity, respectively.”
MethodRashidi, H. H., Hu, B., Pantanowitz, J., Tran, N. K., Liu, S., Chamanzar, A., Gür, M., Chang, C. H., Wang, Y., Tafti, A. P., et al. (2024) · Modern Pathology · doi:10.1016/j.modpat.2024.100663 · Cited by 26
A study on the relationship between depth map quality and the overall 3D video quality of experience
Banitalebi-Dehkordi, A., Pourazad, M. T., & Nasiopoulos, P. (2013) · doi:10.1109/3dtv.2013.6676650 · Cited by 18
A spatiotemporal no-reference video quality assessment model
Konuk, B., Zerman, E., Nur, G., & Akar, G. (2013) · 2013 IEEE International Conference on Image Processing · doi:10.1109/icip.2013.6738012 · Cited by 21
Visual quality indices and lowquality images
Hofbauer, H., & Uhl, A. (2010) · European Workshop on Visual Information Processing · doi:10.1109/euvip.2010.5699105 · Cited by 18
Image-Difference Prediction: From Color to Spectral
Moan, S. L., & Urban, P. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2311373 · Cited by 18
Single-Image Super-Resolution by Subdictionary Coding and Kernel Regression
Yang, W., Yuan, T., Wang, W., Zhou, F., & Liao, Q. (2016) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2016.2523947 · Cited by 18
“The PSNR, MS-SSIM, and VIF results obtained by the competing methods on the test images are listed in Table II.”
MethodInfluentialLow-power DCT-based compressor for wireless capsule endoscopy
Shabani, A., & Timarchi, S. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.03.003 · Cited by 19
Kurzhunov, D., Borowiak, R., Reisert, M., Krafft, A. J., Özen, A. Ç., & Bock, M. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2017.05.029 · Cited by 18
“…image degradation as perceived change in structural information while incorporating image luminance, contrast and structure comparison functions (Wang et al., 2004, 2003), and was used for comparison of reconstruction techniques in MRI (Anand and Sahambi, 2010; Gnahm and Nagel, 2015; Zhu et…”
MethodYang, J., Jiang, B., Wang, Y., Lu, W. B., & Meng, Q. (2017) · Information Sciences · doi:10.1016/j.ins.2017.10.053 · Cited by 18
“[9] Zhou Wang, Eero P Simoncelli, and Alan C Bovik.”
BackgroundMethodAn efficient motion magnification system for real-time applications
Al‐Naji, A., Lee, S., & Chahl, J. (2018) · Machine Vision and Applications · doi:10.1007/s00138-018-0916-0 · Cited by 21
“To simplify the expression, a specific form of the SSIM with α = β = γ = 1 and C3 = C2/2 is given by [35,36]:”
MethodGeometric Transformation Invariant Image Quality Assessment Using Convolutional Neural Networks
Ma, K., Duanmu, Z., & Wang, Z. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8462176 · Cited by 19
“These include SSIM [2], MS-SSIM [22], CW-SSIM [5], and VIF [3].”
MethodSelf-citationA spatiotemporal model of video quality assessment via 3D gradient differencing
Lu, W. B., He, R., Yang, J., Jia, C., & Gao, X. (2018) · Information Sciences · doi:10.1016/j.ins.2018.11.003 · Cited by 19
Shi, C., & Wang, L. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2897344 · Cited by 18
Dense '123' Color Enhancement Dehazing Network
Guo, T., Cherukuri, V., & Monga, V. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00266 · Cited by 19
“Hence, to retain the structure, we employ a MS-SSIM loss function [38, 39].”
MethodDistorted Representation Space Characterization Through Backpropagated Gradients
Kwon, G., Prabhushankar, M., Temel, D., & AlRegib, G. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803228 · Cited by 20
Effective Data Augmentation with Multi-Domain Learning GANs
Yamaguchi, S., Kanai, S., & Eda, T. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.6131 · Cited by 36
A Novel Deep Progressive Image Compression Framework
Cai, C., Chen, L., Zhang, X., Lu, G. S., & Gao, Z. (2019) · Picture Coding Symposium · doi:10.1109/pcs48520.2019.8954500 · Cited by 22
“So we propose to use the multiscale structural similarity index metric (MS-SSIM) [18] to measure the quality of the preview image to save more structural information for better visual quality.”
MethodEmulation of Cosmological Mass Maps with Conditional Generative Adversarial Networks
Perraudin, N., Marcon, S., Lucchi, A., & Kacprzak, T. (2021) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2021.673062 · Cited by 33
“The absolute difference between the MS-SSIM scores of real and fake samples is 0.0018 globally and 0.0012± 0.0009 per cosmology, meaning that generated images are as varied as the original ones.”
BackgroundMethodInfluentialMulti-granularity generative adversarial nets with reconstructive sampling for image inpainting
Xu, L., Zeng, X., Li, W., & Huang, Z. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.04.011 · Cited by 19
Learning synthetic aperture radar image despeckling without clean data
Zhang, G., Li, Z. N., Li, X., et al. (2020) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.14.026518 · Cited by 18
A Viewport-Driven Multi-Metric Fusion Approach for 360-Degree Video Quality Assessment
Azevedo, R. G. D. A., Birkbeck, N., Janatra, I., Adsumilli, B., & Frossard, P. (2020) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme46284.2020.9102936 · Cited by 25
“MultiScale-SSIM [24] is an extension of SSIM [25] for multiple scales.”
MethodSmall sample color fundus image quality assessment based on gcforest
Liu, H., Zhang, N., Jin, S., Xu, D., & Gao, W. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09362-y · Cited by 18
“Multi-scale analysis can greatly improve the quality prediction performance [25, 32, 33].”
BackgroundTian, X. S., Zhang, M., Yang, C., et al. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3014698 · Cited by 18
“By further considering the variations of image resolution, the multiscale structural similarity index (MSSIM) [46] is further used and defined as where M denotes the scale.”
MethodShineOn: Illuminating Design Choices for Practical Video-based Virtual Clothing Try-on
Kuppa, G., Jong, A., Liu, X., Liu, Z., & Moh, T.-S. (2021) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw52041.2021.00025 · Cited by 30
“SSIM [35] is defined by where µ is the average, σ 2 is the variance, and c 1 and c 2 are constants used to stabilize the calculation.”
MethodFast Multi-Focus Fusion Based on Deep Learning for Early-Stage Embryo Image Enhancement
Raudonis, V., Paulauskaitė-Tarasevičienė, A., & Šutienė, K. (2021) · Sensors · doi:10.3390/s21030863 · Cited by 18
“The computations are typically performed in a sliding N × N (by default 11 × 11) Gaussian-weighted window [31].”
MethodMoghari, M. D., Zhou, L., Yu, B., Young, N., Moore, K., Evans, A., Fulton, R., & Kyme, A. Z. (2021) · Physics in Medicine and Biology · doi:10.1088/1361-6560/abe917 · Cited by 18
Document Image Binarization With Stroke Boundary Feature Guided Network
Dang, Q.-V., & Lee, G.-S. (2021) · IEEE Access · doi:10.1109/access.2021.3062904 · Cited by 19
“In the main task, the input employs the degraded document image I org and its edge map We apply hybrid loss [24] for l i l i = l bce + l iou + l ssim (5) where l bce , l iou , l ssim define BCE loss [35], IOU loss [36], and SSIM loss [37], respectively.”
MethodQuality Evaluation of Holographic Images Coded With Standard Codecs
Amirpour, H., Pinheiro, A., Fonseca, E., Ghanbari, M., & Pereira, M. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3096059 · Cited by 18
“Five objective metrics were selected, namely, PSNR, SSIM [31], MS-SSIM [32], FSIM [33], and VIFp [34].”
MethodImproving Generalizability in Limited-Angle CT Reconstruction with Sinogram Extrapolation
Wang, C., Zhang, H., Li, Q., Shang, K., Lyu, Y., Dong, B., & Zhou, S. K. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87231-1_9 · Cited by 29
“5) [23] and peak signal-to-noise ratio (PSNR) [22].”
A New Full-Reference Image Quality Metric for Motion Blur Profile Characterization
Abdullah-Al-Mamun, M., Tyagi, V., & Zhao, H. (2021) · IEEE Access · doi:10.1109/access.2021.3130177 · Cited by 18
“C 1 and C 2 , and C 3 are constants defined by, where, L is the dynamic range of the image and k 1 = 0.01 and k 2 = 0.03 [16].”
BackgroundInfluentialDegraded Reference Image Quality Assessment
Athar, S., & Wang, Z. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3234498 · Cited by 25
“many combinations of FR methods (PSNR, MSSSIM [29],”
MethodInfluentialSelf-citationVisual quality improvement techniques of HDPhoto/JPEG-XR
Richter, T. (2008) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2008.4712398 · Cited by 19
CNN-based PET sinogram repair to mitigate defective block detectors
Whiteley, W., & Gregor, J. (2019) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ab4919 · Cited by 24
“(7) In the reconstructed image domain MS-SSIM, which uses a perception-based model, was used to compare the similarity between reference images and images reconstructed from sinograms with missing data and sinograms corrected with each repair method.”
MethodInfluentialAssessment of the Segmentation of RGB Remote Sensing Images: A Subjective Approach
Kazakevičiūtė-Januškevičienė, G., Janusonis, E., Baušys, R., Limba, T., & Kiškis, M. (2020) · Remote Sensing · doi:10.3390/rs12244152 · Cited by 19
“MS-SSIM [37] Multi-scale Structural Similarity index structural distortion”
MethodAn improved DC recovery method from AC coefficients of DCT-transformed images
Li, S., Ahmad, J. J., Saupe, D., & Kuo, C. ‐. J. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5653467 · Cited by 21
“We provide experimental results to demonstrate the superior performance of the improved DC recovery method in terms of PSNR and nine objective image quality assessment (IQA) metrics in the MeTriX MuX Visual Quality Assessment Package [9], which includes SSIM [10], MS-SSIM [11], IFC [12], VIF [13], etc.”
MethodSimulated Annealing for JPEG Quantization
Hopkins, M., Mitzenmacher, M., & Wagner-Carena, S. (2018) · DCC · doi:10.1109/dcc.2018.00065 · Cited by 18
“Their analysis suggests that a structural method, SSIM, is one of the most effective methods in approaching the HSV standards set by psychovisual databases while also beating other methods such as VIF (Visual Information Fidelity) in time complexity.”
BackgroundMethodInfluentialBobkov, D., Titov, V., Alanov, A., & Vetrov, D. (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/cvpr52733.2024.00892 · Cited by 32
A Triple Self-Embedding Fragile Watermarking Scheme for Image Tamper Detection and Recovery
Ozkaya, H., & Aslantaş, V. (2024) · IEEE Access · doi:10.1109/access.2024.3466611 · Cited by 16
“The Multi-Scale Structural Similarity Index Measure (MS-SSIM) is proposed to compare the quality of complex-structured images, especially at levels where distortions become visible [45].”
MethodOpenDIC: An Open-Source Library and Performance Evaluation for Deep-learning-based Image Compression
Gao, W., Zheng, H., Zhang, C., Zheng, K., Yu, Z., Li, Y., Ye, H., & Zhang, Y. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3685519 · Cited by 19
Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption
Du, C., Wu, T., Ma, K., & Zhang, L. (2025) · 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/cvpr52734.2025.01189 · Cited by 64
GS-Pose: Generalizable Segmentation-Based 6D Object Pose Estimation with 3D Gaussian Splatting
Cai, D., Heikkilä, J., & Rahtu, E. (2025) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv66043.2025.00097 · Cited by 46
“The loss function L gs is defined as a combination of the losses based on the image structural similarity (SSIM) and Multi-Scale SSIM [52]: The optimization is initialized with an identity transformation and iteratively updates T ∗ gs using the AdamW optimizer [29] with the cosine annealing…”
Video quality assessment using visual attention computational models
Akamine, W. Y. L., & Farias, M. C. Q. (2014) · Journal of Electronic Imaging · doi:10.1117/1.jei.23.6.061107 · Cited by 21
“For our tests, we selected four FR quality metrics of known good performance: the video quality metric (VQM),(45) the motion-based video integrity evaluation (MOVIE),(46) the SSIM,(1) and the multiscale structural similarity index (MSSSIM).(47) In this section, we briefly describe each of these metrics.”
MethodInfluentialA better way to monitor haze through image based upon the adjusted LeNet-5 CNN model
Fan, Y., Rui, X., Poslad, S., Zhang, G., Tian, Y., Xu, X., & Song, X. (2019) · Signal Image and Video Processing · doi:10.1007/s11760-019-01574-6 · Cited by 17
“3 [38, 39]).”
Liu, C.-H., Chang, H., & Park, T. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00257 · Cited by 20
“where MS-SSIM index is defined in [26].”
Object-Based Image Coding: A Learning-Driven Revisit
Xia, Q., Liu, H., & Ma, Z. (2020) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme46284.2020.9102810 · Cited by 18
“07 bpp (or >340x compression ratio), MS-SSIM offers more meaningful quality measurement close to our subjective sensation [21].”
BackgroundMethodInfluentialPersonalized quantification of facial normality: a machine learning approach
Boyaci, O., Serpedin, E., & Stotland, M. A. (2020) · Scientific Reports · doi:10.1038/s41598-020-78180-x · Cited by 17
“…between any two images in image space via perceptual similarity (LPIPS) 26 , structural similarity (mean structural similarity index measure—MSSIM) 27 and peak signal-to-noise ratio (PSNR) techniques 28 , as well as in latent space using Bray–Curtis distance 29 and correlation distance measures.”
MethodDeep HDR Hallucination for Inverse Tone Mapping
Marnerides, D., Bashford‐Rogers, T., & Debattista, K. (2021) · Sensors · doi:10.3390/s21124032 · Cited by 23
“[7], using the perceptually uniform (PU) [45] encoded PSNR, SSIM [46], MS-SSIM [47] and HDR-VDP-2 [48].”
MethodUniversal Rate-Distortion-Perception Representations for Lossy Compression
Zhang, G., Qian, J., Chen, J., & Khisti, A. J. (2025) · IEEE Transactions on Information Theory · doi:10.1109/tit.2025.3584291 · Cited by 55
“Common full-reference metrics include MSE, SSIM/MS-SSIM [36, 37], PSNR or deep feature based distances [16, 41].”
The Impact of Resampling and Denoising Deep Learning Algorithms on Radiomics in Brain Metastases MRI
Moummad, I., Jaudet, C., Lechervy, A., Valable, S., Raboutet, C., Soilihi, Z., Thariat, J., Falzone, N., Lacroix, J., Batalla, A., et al. (2021) · Cancers · doi:10.3390/cancers14010036 · Cited by 19
“MSE: Mean Squared Error MGE: Mean Gradient Error MS_SSIM: Multi-Scale SSIM corresponding to multiple SSIM image evaluations at different image scales [22].”
Tile-Based Panoramic Video Quality Assessment
Jiang, Z., Xu, Y., Sun, J., Hwang, J., Zhang, Y., & Appleby, S. C. (2021) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2021.3136748 · Cited by 19
A Full-Reference Quality Assessment Metric for Fine-Grained Compressed Images
Zhang, Z., Sun, W., Min, X., Wang, T., Lu, W., & Zhai, G. (2021) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip53242.2021.9675389 · Cited by 23
“To analyse the effectiveness of different IQA metrics, we choose several state-of-the-art FR-IQA methods for comparison, which include: PSNR, SSIM [3], VSI [4], MS-SSIM [5], IW SSIM [6], FSIM [7], MAD [8], GSMD [9], IFC [13], PieAPP [15], and LPIPS [17].”
MethodHybrid Single Image Super-Resolution Algorithm for Medical Images
El‐Shafai, W., Mohamed, E. M., Zeghid, M., et al. (2022) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.028364 · Cited by 17
Saliency-Guided Local Full-Reference Image Quality Assessment
Varga, D. (2022) · Signals · doi:10.3390/signals3030028 · Cited by 19
Conformer and Blind Noisy Students for Improved Image Quality Assessment
Conde, M. V., Burchi, M., & Timofte, R. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00108 · Cited by 21
“Since that, various FR metrics have been developed to take into account various aspects of human quality perception, e.g., information-theoretic criterion [46] or structural similarity [61,68].”
BackgroundInfluentialLAN: Lightweight Attention-based Network for RAW-to-RGB Smartphone Image Processing
Raimundo, D. W., Ignatov, A., & Timofte, R. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00096 · Cited by 28
“An extension of SSIM, called multiscale SSIM (MS-SSIM), also computes SSIM on downsampled versions of the input and was shown to provide better results than the original implementation [33].”
ResultImage-Driven Harmonious Color Palette Generation for Diverse Information Visualization
Liu, S.-Q., Tao, M.-T., Huang, Y., Wang, C.-B., & Li, C.-H. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3226218 · Cited by 19
“Then, ‘ bce was formulated as follows: SSIM loss [52] measures the structural similarity between images.”
MethodCycleGAN Clinical Image Augmentation Based on Mask Self-Attention Mechanism
Liu, J., Wang, Z., Zhang, Y., Traverso, A., Dekker, A. L. A. J., Zhang, Z., & Chen, Q. (2022) · IEEE Access · doi:10.1109/access.2022.3211670 · Cited by 17
“Their loss function equation is as follows : To avoid excessive transfer on the input and output hierarchy and make the generated images more realistic, multi-level structure similarity(MS-SSIM) [37] is introduced in the identity mapping loss.”
MethodSelf-citationFully automatic segmentation and monitoring of choriocapillaris flow voids in OCTA images
López-Varela, E., de Moura, J., Novo, J., Fernández‐Vigo, J. I., Moreno-Morillo, F. J., & Ortega, M. (2023) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2022.102172 · Cited by 17
Subjective and Objective Video Quality Assessment of High Dynamic Range Sports Content
Shang, Z., Chen, Y., Wu, Y., Wei, H., & Sethuraman, S. (2023) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw58289.2023.00062 · Cited by 19
“Here we present the results of a few popular FR VQA models: peak signal-to-noise ratio (PSNR), SSIM, MS-SSIM [30], SpEEDQA [6], ST-RRED [28] and VMAF [7].”
MethodIrisGuideNet: Guided Localization and Segmentation Network for Unconstrained Iris Biometrics
Muhammad, J., Wang, C., Wang, Y., et al. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3268504 · Cited by 17
Chen, H., Shao, F., Chai, X., Jiang, Q., Meng, X., & Ho, Y. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3286542 · Cited by 22
“The FR-IQA methods include 12 hand-crafted feature-based models: SSIM [12], VIF [28], FSIM [42], multi-scale SSIM (MS-SSIM) [43], IW-SSIM [44], PSNR, most apparent distortion (MAD) [45], visual saliency-induced method (VSI) [46], gradient magnitude similarity Authorized licensed use limited to the…”
MethodPerceptual Quality Analysis in Deep Domains Using Structure Separation and High-Order Moments
Xian, W., Zhou, M., Fang, B., Xiang, T., Weijia Jia, B., & Chen, B. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3293730 · Cited by 18
“Gao et al. [22] proposed the deep similarity (DeepSim) method, which measures the SSIM be-tween test and reference images in the feature space produced by VGG-16.”
MethodInfluentialSørensen, K. A., Kusk, A., Heiselberg, P., et al. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3295002 · Cited by 17
“We likewise experimented with, e.g., the multiscale SSIM (MS-SSIM) [27] and root-mean-square-error.”
BackgroundMethodInfluentialNeRF-QA: Neural Radiance Fields Quality Assessment Database
Martin, P., Rodrigues, A., Ascenso, J., & Queluz, M. P. (2023) · International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex58391.2023.10178625 · Cited by 19
“In the NeRF related literature, five objective quality metrics have been typically used to evaluate the view synthesis results, namely PSNR, SSIM [9], MS-SSIM [10], LPIPS [11], and JOD [12].”
MethodSpatio-temporal prediction of regional land subsidence via ConvLSTM
Leng, J. P., Gao, M., Gong, H., et al. (2023) · Journal of Geographical Sciences · doi:10.1007/s11442-023-2169-8 · Cited by 17
“According to previous experiments (Wang et al., 2003), we set β1=γ1=0.”
MethodInfluentialImproved Few-Shot SAR Image Generation by Enhancing Diversity
Bao, J., Yu, W., Yang, K., Liu, C., & Cui, T. J. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3352237 · Cited by 18
Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction
Chen, S.-K., Yen, H.-L., Liu, Y.-L., Chen, M.-H., Hu, H.-N., Peng, W.-H., & Lin, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01194 · Cited by 30
“We employ PSNR, SSIM [ 49], and MS-SSIM [50] as the metrics for evaluating the qualities of [23].”
MethodUncertainty-Aware Deep Video Compression With Ensembles
Ma, W., Li, J., Li, B., & Lu, Y. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3372352 · Cited by 21
“…loss given by where R mv (ˆ a t ) and R res (ˆ b t ) represent the numbers of bits used to encode the motion vectors and the residual, D ( F t , ˆ F t ) measures the distortion in mean squared error or multi-scale structural similarity [42], and λ is the hyperparameter controlling the trade-off.”
BackgroundSpectral Prompt Tuning: Unveiling Unseen Classes for Zero-Shot Semantic Segmentation
Xu, W., Xu, R., Wang, C., Xu, S., Guo, L., Zhang, M., & Zhang, X. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i6.28456 · Cited by 33
HF-T2CR: High-Fidelity Thin and Thick Cloud Removal in Optical Satellite Images Through SAR Fusion
Li, X., Zhao, X., Wang, F., & Ren, P. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3416128 · Cited by 27
“Loss functions used in this article can be divided into three terms: the reconstruction loss, the MS-SSIM loss [44], and the adversarial loss.”
MethodBo, Y., Shao, S., & Tao, M. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3447870 · Cited by 24
Visible-to-Infrared Image Translation for Matching Tasks
Ma, D., Li, S., Su, J., Xian, Y., & Zhang, T. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3468456 · Cited by 30
“Image quality was measured by the peak signal-to-noise ratio (PSNR) [78], structural similarity index measure (SSIM), multiscale structural similarity index measure (MS-SSIM) [79], learned perceptual image patch similarity (LPIPS) [80], and Fréchet inception distance (FID) [81].”
MethodA novel SVD-based image quality assessment metric
Wang, S., Deng, C.-W., Lin, W., Zhao, B., & Chen, J. (2013) · 2013 IEEE International Conference on Image Processing · doi:10.1109/icip.2013.6738087 · Cited by 12
Capodiferro, L., Jacovitti, G., & Claudio, E. D. D. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2165293 · Cited by 21
No-reference Harmony-Guided Quality Assessment
Chamaret, C., & Urban, F. (2013) · IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2013.161 · Cited by 16
JPEG on STEROIDS: Common optimization techniques for JPEG image compression
Richter, T. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532319 · Cited by 17
Quality assessment for virtual reality technology based on real scene
Jiang, B., Yang, J.-C., Jiang, N., Lv, Z., & Meng, Q. (2016) · Neural computing & applications (Print) · doi:10.1007/s00521-016-2828-0 · Cited by 16
RetractedNo-reference image quality assessment using local binary pattern in the wavelet domain
Rezaie, F., Helfroush, M. S., & Danyali, H. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4432-4 · Cited by 20
“IEEE Trans Image Process 20:64–75 Table 4 Median srocc comparison across 1000 train-test combinations on the TID2008 database algorithm Type JP2K JPEG WN Blur All PSNR FR 0.8762 0.9029 0.9173 0.7801 0.8592 SSIM 0.9405 0.9462 0.9824 0.9004 0.9066 MS-SSIM 0.9793 0.9883 0.9645 0.9488 0.9511 BLIINDS-II NR 0.9157 0.8901 0.…”
MethodInfluentialA full reference stereoscopic video quality assessment metric
Appina, B., Manasa, K., & Channappayya, S. S. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952509 · Cited by 19
“MS-SSIM [29] is a top down approach which computes the structural similarity at different scales and hence, the spatial quality for each frame of the left and the right view is given by Qisl = (1− (MS-SSIM(H i spl , Histl ))) Qisr = (1− (MS-SSIM(H i spr , Histr ))) where, Hispl represents the frame i of the pristine p…”
BackgroundInfluentialEstimating just‐noticeable distortion for images/videos in pixel domain
Uzair, M., & Dony, R. D. (2017) · IET Image Processing · doi:10.1049/iet-ipr.2016.1120 · Cited by 17
“Kelly [23] presented a spatio-temporal CSF model which was based on his experimental data collected for retinally stabilised travelling wave stimuli.”
MethodStrategies of SAR image lossy compression by JPEG2000 and SPIHT
Kozhemiakin, R. A., Abramov, S., Лукин, В. В., et al. (2017) · Mediterranean Conference on Embedded Computing (MECO) · doi:10.1109/meco.2017.7977176 · Cited by 17
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.