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 1,401–1,500 of 6,047
Bag-of-words feature representation for blind image quality assessment with local quantized pattern
Xie, X., Zhang, Y., Wu, J., Shi, G., & Dong, W. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.05.034 · Cited by 23
Color and sharpness assessment of single image dehazing
Khoury, J. E., Moan, S. L., Thomas, J., et al. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5122-y · Cited by 24
“We selected Multi-Structural Similarity (MS-SSIM) [53], that predicts image quality considering contrast, structure and luminance.”
MethodEthanol: A Software-Defined Wireless Networking architecture for IEEE 802.11 networks
Moura, H. D., Alves, A. R., Borges, J. R. A., et al. (2019) · Computer Communications · doi:10.1016/j.comcom.2019.10.010 · Cited by 24
Crowd counting via scale-communicative aggregation networks
Yuan, L., Qiu, Z., Liu, L., Wu, H., Chen, T., Chen, P., & Lin, L. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.05.042 · Cited by 21
Chaudhuri, C., & Robertson, C. (2020) · Water · doi:10.3390/w12123353 · Cited by 35
Combining Tensor Slice and Singular Value for Blind Light Field Image Quality Assessment
Pan, Z., Yu, M., Jiang, G., Xu, H., & Ho, Y. (2021) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2021.3056959 · Cited by 25
“Specifically, ten 2D FR methods including PSNR, SSIM [8], VIF [9], MS-SSIM [10], IW-SSIM [11], FSIM [12], GSM [13], GMSD [14], HDR-VDP-2 [15] and PSIM [16], four 2D NR methods including BRISQUE [22], GM-LOG [23], SSEQ [24] and OG-IQA [25], one 3D FR method namely Chen’s method [17], two multi-view…”
MethodModular Framework and Instances of Pixel-Based Video Quality Models for UHD-1/4K
Göring, S., Rao, R. R. R., Feiten, B., & Raake, A. (2021) · IEEE Access · doi:10.1109/access.2021.3059932 · Cited by 24
“Most video quality models have their origin in image quality estimation, such as Structural Similarity Index Measure (SSIM) [88], [89] or Visual Information Fidelity (VIF) [79].”
BackgroundMethodIQMA Network: Image Quality Multi-scale Assessment Network
Guo, H., Bin, Y., Hou, Y., Zhang, Q., & Luo, H. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00055 · Cited by 37
“The methods include shallow methods PSNR [2] and SSIM [26], and deep learning-based methods such as LPIPS [30], PieAPP [20], DISTS [8], and SWD [10].”
MethodInfluentialBoundary-Oriented Binary Building Segmentation Model With Two Scheme Learning for Aerial Images
Lee, K., Kim, J. H., Lee, H., Park, J., Choi, J. P., & Hwang, J. Y. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3089623 · Cited by 26
Harmonious Textual Layout Generation Over Natural Images via Deep Aesthetics Learning
Li, C., Zhang, P., & Wang, C. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3097900 · Cited by 26
“Accordingly, to obtain more accurate regional segmentation and clear boundaries, we use a hybrid training loss: where L B (Θ) and L S (Θ) denote BCEWithLogits loss [39] and SSIM loss [40], Θ is the BASNet model parameters.”
MethodLGGD+: Image Retargeting Quality Assessment by Measuring Local and Global Geometric Distortions
Peng, Z., Jiang, Q., Shao, F., Gao, W., & Lin, W. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3112933 · Cited by 24
Deep image synthesis from intuitive user input: A review and perspectives
Xue, Y., Guo, Y.-C., Zhang, H., Xu, T., Zhang, S., & Huang, X. (2021) · Computational Visual Media · doi:10.1007/s41095-021-0234-8 · Cited by 30
Saliency-Guided Remote Sensing Image Super-Resolution
Liu, B., Zhao, L., Li, J., Zhao, H., Liu, W., Li, Y., Wang, Y., Chen, H., & Cao, W. (2021) · Remote Sensing · doi:10.3390/rs13245144 · Cited by 24
“where ` bce, ` (k) ssim, and ` (k) iou denote BCE loss [63], SSIM loss [64], and IoU loss [65], respectively.”
BackgroundMethodRectified Wasserstein Generative Adversarial Networks for Perceptual Image Restoration
Ma, H., Liu, D., & Wu, F. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3185316 · Cited by 29
“Note that multi-scale evaluation is used in many image quality assessment methods, notably multi-scale structural similarity (MS-SSIM) [45].”
BackgroundAhmad, I., & Shin, S. (2022) · Electronics · doi:10.3390/electronics11162514 · Cited by 28
Motyl, M., & Madej, Ł. (2022) · Archives of Civil and Mechanical Engineering · doi:10.1007/s43452-022-00531-4 · Cited by 24
“The SSIM index is a quality measurement metric calculated based on the computation of three major components termed luminance, contrast, and structural or correlation term [34]:”
Method2C-Net: integrate image compression and classification via deep neural network
Liu, L., Chen, T., Liu, H., Pu, S., Wang, L., & Shen, Q. (2022) · Multimedia Systems · doi:10.1007/s00530-022-01026-1 · Cited by 28
“Since HVS and DNN-based feature extraction are both sensitive to the structure information of image contents [58, 59], we select the MultiScale Structural SIMilarity index (MS-SSIM) as the distortion measurement for image reconstruction, which is a perception loss widely used in image quality assessment [60] and image…”
MethodLiao, H., Jiang, Q., Jin, X., Liu, L., Liu, L., Lee, S., & Zhou, W. (2022) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3218833 · Cited by 28
“Different from SSIM, multi-scale SSIM [54] adopts different resolutions, which makes up for the disadvantage that conventional single-scale SSIM loss is only appropriate for specific settings.”
MethodNo-reference perceptual CT image quality assessment based on a self-supervised learning framework
Lee, W.-Y., Cho, E., Kim, W., Choi, H., Beck, K., Yoon, H., Baek, J., & Choi, J.-H. (2022) · Machine Learning: Science and Technology · doi:10.1088/2632-2153/aca87d · Cited by 33
“…in comparison with other representative FR-and NR-IQA methods, including root mean square error (RMSE), PSNR, SSIM, multi-scale (MS)-SSIM [40], gradient magnitude similarity deviation (GMSD) [41], feature similarity index (FSIM) [42], noise quality measure (NQM) [43], visual information…”
BackgroundLin, B., Fan, X., Li, D., et al. (2023) · Photonics · doi:10.3390/photonics10020204 · Cited by 24
“The Structural Similarity Index ( SSIM ) is a common indicator to evaluate the image quality and measure the similarity of images [55].”
Background3-D Computed Laminography Based on Prior Images and Total Variation
Gui, Z., Liu, Y., Liu, Y., Liu, W., Yan, R., Wang, L., Zhang, P., Zhang, Q., & Shu, H. (2023) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2023.3246099 · Cited by 24
“Note that higher MSSIM, CC or UQI shows a higher quality of reconstruction.”
InfluentialLocally Adaptive Channel Attention-Based Spatial–Spectral Neural Network for Image Deblurring
Lee, H. S., & Cho, S. I. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3250509 · Cited by 29
“(MS-SSIM) [70], and mean square error (MSE) [71] which have been widely employed for the performance comparison in the field of image enhancement to measure the performance of the proposed LACA-SSN and previous image-deblurring methods.”
MethodRemote Sensing Image Compression Based on the Multiple Prior Information
Fu, C., & Du, B. (2023) · Remote Sensing · doi:10.3390/rs15082211 · Cited by 33
“MSSSIM is based on Structural Similarity (SSIM) but is formulated in a multi-scale manner as follows: MSSSIM = [lm(x, y)]αm M ∏ i=1 [cj(x, y)] β j [sj(x, y)] ηj (4) where cj(x, y) and sj(x, y) denote the contrast comparison and the structure comparison for the jth scale image.”
BackgroundMethodInfluentialLearned Video Compression via Heterogeneous Deformable Compensation Network
Wang, H., Chen, Z., & Chen, C. W. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3289763 · Cited by 35
“Note that in this training period, D com only denotes mean-square error (MSE) in our PSNR and MS-SSIM [39] models.”
MethodEditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points
Zheng, C., Lin, W., & Xu, F. (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/cvpr52729.2023.00804 · Cited by 45
“For a real data sequence with 2 N frames, we pick out N frames with even indices as the training set, and the other N frames Method PSNR ↑ MS-SSIM ↑ LPIPS ↓ HyperNeRF [28] 30 with odd indices are used as ground truth for testing.”
MethodSingle image super-resolution approaches in medical images based-deep learning: a survey
El‐Shafai, W., Ali, A. M., El‐Nabi, S. A., El‐Rabaie, E. M., & El‐Samie, F. E. A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16197-w · Cited by 29
“Multi-Scale SSIM (MS-SSIM) [118] is preferred to SSIM in image quality assessment.”
No-Reference Virtual Reality Image Quality Evaluator Using Global and Local Natural Scene Statistics
Poreddy, A. K. R., Ganeswaram, R. B. C., Appina, B., Kokil, P., & Pachori, R. B. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3322995 · Cited by 26
“Many works [19], [64] studied the natural scene statistics (NSS) of an image across multiple-scales.”
BackgroundMethodA Study of Subjective and Objective Quality Assessment of HDR Videos
Shang, Z., Ebenezer, J. P., Venkataramanan, A. K., Wu, Y., Wei, H., Sethuraman, S., & Bovik, A. C. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3333217 · Cited by 33
“More recent popular VQA models include Structural Similarity (SSIM) [19], Multiscale SSIM (MS-SSIM) [29], Gradient Magnitude Similarity Deviation (GMSD) [30], most apparent distortion (MAD) [31], visual information fidelity (VIF) [20], and FSIM [32], among others [33], [34], [35], [36].”
MethodSelf-citationPacket losses and objective video quality metrics in H.264 video streaming
Tommasi, F., Luca, V. D., & Melle, C. (2014) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2014.12.003 · Cited by 24
A New Look to Multichannel Blind Image Deconvolution
Mseddi, W. S., Abed‐Meraim, K., & Beghdadi, A. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2018566 · Cited by 24
“The objective quality of the restored image is evaluated by means of a structural objective image quality index namely the Structural Similarity Index Measure (SSIM) introduced in [34].”
MethodCSV: Image quality assessment based on color, structure, and visual system
Temel, D., & AlRegib, G. (2016) · Signal Processing Image Communication · doi:10.1016/j.image.2016.08.008 · Cited by 24
“In the exotic category, FSIM, FSIMc, and MS-SSIM are the highest performing quality estimators in both correlation types and IW-SSIM is also among the best performers in Spearman correlation category.”
MethodInfluentialEdge preservation ratio for image sharpness assessment
Chen, L., Jiang, F., Zhang, H., Wu, S., Yu, S., & Xie, Y. (2016) · World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2016.7578241 · Cited by 26
“and applied to filtered and down-sampled images [10].”
Quality evaluation of no‐reference MR images using multidirectional filters and image statistics
Jang, J., Bang, K., Jang, H., Hwang, D., & Initiative, A. D. N. (2018) · Magnetic Resonance in Medicine · doi:10.1002/mrm.27084 · Cited by 28
“The graphs in Figure 6 compare the QEMDIM scores with values obtained using the full-reference IQA meth-ods RMSE and SSIM.”
BackgroundInfluentialLaBGen-P-Semantic: A First Step for Leveraging Semantic Segmentation in Background Generation
Laugraud, B., Piérard, S. L., & Droogenbroeck, M. V. (2018) · Journal of Imaging · doi:10.3390/jimaging4070086 · Cited by 24
“• Multi-scale structural similarity index (MS-SSIM, ↑, ∈ [−1, 1]) [23]: pyramidal version of the structural similarity index (SSIM), which measures the change of structural information for approximating the perceived distortion between an input and a ground-truth background image.”
BackgroundQuality Assessment of HDR/WCG Images Using HDR Uniform Color Spaces
Rousselot, M., Meur, O. L., Cozot, R., & Ducloux, X. (2019) · Journal of Imaging · doi:10.3390/jimaging5010018 · Cited by 26
“This method can be used for any metrics using the luminance corrected with the gamma function, such as PSNR, SSIM [8], VIF [9], Multiscale-SSIM [10] (MS-SSIM).”
MethodSecure telemedicine using RONI halftoned visual cryptography without pixel expansion
Bakshi, A., & Patel, A. K. (2019) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2019.03.004 · Cited by 25
Surprise-Based JND Estimation for Images
Wang, H., Wang, S., Li, T., Yin, H., & Yu, L. (2019) · IEEE Signal Processing Letters · doi:10.1109/lsp.2019.2957647 · Cited by 23
“In this letter, the performance of JND models is measured in terms of PSNR, Multi-scale structural similarity (MS-SSIM) [30] and mean opinion score (MOS).”
MethodInfluentialWang, M., Li, X., & Chau, P. Y. K. (2020) · Information Systems Frontiers · doi:10.1007/s10796-020-09981-8 · Cited by 25
Deep Medical Image Reconstruction with Autoencoders using Deep Boltzmann Machine Training
Saravanan, S., & Juliet, S. (2020) · EAI Endorsed Transactions on Pervasive Health and Technology · doi:10.4108/eai.24-9-2020.166360 · Cited by 24
Inverse Transport NetworksPreprint
Che, C., Luan, F., Zhao, S., Bala, K., & Gkioulekas, I. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.10820 · Cited by 34
“We then compare the rendered and input images using two different metrics: (1) RMSE, and (2) the multi-scale structural similarity index (MS-SSIM) [65], as a representative perceptually-motivated image quality metric.”
MethodA Small Object Real-Time Detection Method for Power Line Inspection in Low-Illuminance Environments
Zhao, Y., Wu, J., Chen, W., Wang, Z., Tian, Z., Yu, F. R., & Leung, V. C. M. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3378651 · Cited by 26
Self-citationMedical steganography: Enhanced security and image quality, and new S-Q assessment
Peng, Y., Fu, C., Zheng, Y., Tian, Y., Cao, G., & Chen, J. (2024) · Signal Processing · doi:10.1016/j.sigpro.2024.109546 · Cited by 23
DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes
Yan, H., Ke, Z., Zhou, X., Qiu, T., Shi, X., & Jiang, 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/cvpr52733.2024.02172 · Cited by 25
“We employ PSNR and MS-SSIM [46] as metrics to evaluate video reconstruction quality, and bits per pixel (bpp) as an indicator of video compression performance.”
MethodQuantum adversarial generation of high-resolution images
Ma, Q., Hao, C., Si, N., Chen, G., Zhang, J., & Qu, D. (2025) · EPJ Quantum Technology · doi:10.1140/epjqt/s40507-024-00304-3 · Cited by 38
Deep learning techniques for atmospheric turbulence removal: a review
Hill, P., Anantrasirichai, N., Achim, A., & Bull, D. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-024-11086-6 · Cited by 43
Dumić, E., Grgić, S., & Grgić, M. (2014) · Signal, Image and Video Processing · doi:10.1007/s11760-014-0654-3 · Cited by 22
“When comparing correlation in each database separately, Tables 6, 7, 8, MAD measure performs best among all tested measures, because it has the highest correlation in 3 different databases using Pearson’s correlation and 4 databases using Spearman’s correlation.”
MethodBlind image quality assessment for multiply distorted images via convolutional neural networks
Fu, J., Wang, H., & Zuo, L. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7471841 · Cited by 25
“, five representative and outstanding FR-IQA methods including PSNR, SSIM [7], MSSSIM [8], FSIM [9] and GMSD [10], and four state-of-the-art blind IQA methods, including DIIVINE [12], BLIINDSII [13], BRISQUE [14] and CNN-KangLe [16].”
BackgroundMethodA No Reference Image Quality Assessment Metric Based on Visual Perception
Fu, Y. H., & Wang, S. (2016) · Algorithms · doi:10.3390/a9040087 · Cited by 24
“SSIM [5], MS-SSIM [6] and VSNR [7] are examples of successful FR-IQA algorithms.”
MethodZhang, Y., Ngan, K. N., Ma, L., & Li, H. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2746260 · Cited by 23
“Traditional image quality assessment metrics, such as mean square error (MSE), peak-signal-to-noise ratio (PSNR) [28], structural similarity (SSIM) [29], [30] and some recent quality”
Hong, W., & Yu, L. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2780285 · Cited by 24
No-Reference Light Field Image Quality Assessment Based on Micro-Lens Image
Luo, Z., Zhou, W., Shi, L., & Chen, Z. (2019) · Picture Coding Symposium · doi:10.1109/pcs48520.2019.8954551 · Cited by 28
“We conducted comparison experiments between our proposed model and several FR, RR and NR metrics, including nine 2D-FR metrics [10–12, 28–32], three 2D-NR metrics [15,”
MethodThe Performance of Quality Metrics in Assessing Error-Concealed Video Quality
Kazemi, M., Ghanbari, M., & Shirmohammadi, S. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2984356 · Cited by 15
Blind Image Quality Assessment for Super Resolution via Optimal Feature Selection
Beron, J., Benítez-Restrepo, H. D., & Bovik, A. C. (2020) · IEEE Access · doi:10.1109/access.2020.3014497 · Cited by 25
Self-citationZoom-to-Inpaint: Image Inpainting with High-Frequency Details
Kim, S. Y., Aberman, K., Kanazawa, N., Garg, R. D., Wadhwa, N., Chang, H., Karnad, N., Kim, M., & Liba, O. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00063 · Cited by 39
“For quantitative evaluation, we measure the PSNR, SSIM [44], MS-SSIM (multi-scale SSIM) [45] and L1 error of the output inpainted images.”
MethodRen, Y., Liu, B., Yang, S., et al. (2021) · Geophysics · doi:10.1190/geo2020-0370.1 · Cited by 23
Testolina, M., Upenik, E., Ascenso, J., et al. (2021) · International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex51781.2021.9465445 · Cited by 24
“Successively, different variants of this metric were proposed, notably, the Multi-Scale Structural Similarity Index (MS-SSIM) [13], which assesses the SSIM at multiple resolutions and viewing conditions, and the Information Content Weighted Structural Similarity Measure (IW-SSIM) [14], which…”
MethodCSANet: High Speed Channel Spatial Attention Network for Mobile ISP
Hsyu, M.-C., Li, Y., Chen, C.-H., Chen, C., & Tsai, W.-C. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00282 · Cited by 31
“Finally, the total loss is expressed as: Ltotal = Lchar + αLp + βLSSIM (4) where α and β are set to 0.001 and 0.1, respectively.”
MethodInfluentialImage Compression Using Deep Learning: Methods and Techniques
Abd-Alzhra, A. S., & Al-Tamimi, M. S. H. (2022) · Iraqi Journal of Science · doi:10.24996/ijs.2022.63.3.34 · Cited by 30
Joint Frequency and Image Space Learning for MRI Reconstruction and Analysis
Singh, N., Iglesias, J. E., Elfar Adalsteinsson, A., Dalca, A. V., & Golland, P. (2022) · The Journal of Machine Learning for Biomedical Imaging · doi:10.59275/j.melba.2022-16cc · Cited by 38
Qiao, N., Dong, L., & Sun, C. (2022) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2022.3227424 · Cited by 25
“Inspired by literature [23], we propose an adaptive loss function, which covers the improved MS-SSIM [24] loss and improved Smooth - (cid:8) 1 [25] loss.”
MethodDirect reconstruction for simultaneous dual-tracer PET imaging based on multi-task learning
Zeng, F., Fang, J., Muhashi, A., et al. (2023) · EJNMMI Research · doi:10.1186/s13550-023-00955-w · Cited by 24
An Efficient Approach for Underwater Image Improvement: Deblurring, Dehazing, and Color Correction
Espinosa, A. R., McIntosh, D., & Albu, A. B. (2023) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw58289.2023.00026 · Cited by 24
“with α and β default parameters suggested in the original study [33].”
BackgroundNTIRE 2023 HR NonHomogeneous Dehazing Challenge Report
Ancuti, C. O., Ancuți, C., Vasluianu, F.-A., Timofte, R., Zhou, H., Dong, W. F., Liu, Y., Chen, J., Liu, Y., Huan, L., et al. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00180 · Cited by 25
“for attention map, perception loss [36], multi-scale structure similarity loss [64], and adversarial loss [77], respectively.”
BackgroundDyLiN: Making Light Field Networks Dynamic
Yu, H., Julin, J., Milacski, Z. Á., Niinuma, K., & Jeni, L. A. (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/cvpr52729.2023.01193 · Cited by 36
“Intuitively, PSNR is a pixelwise score, while SSIM and MS-SSIM also take pixel correlations and multiple scales into account, respectively, yet all of these tend to favor blurred images.”
MethodInfluentialAn Efficient Breast Cancer Segmentation System based on Deep Learning Techniques
Shaaban, S. M., Nawaz, M. A., Said, Y., & Barr, M. (2023) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.6518 · Cited by 25
“To improve the definition of organ boundaries, a loss function called the multiscale structural similarity index (MS-SSIM) [33] was used.”
MethodPerceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front‐Facing Views
Liang, H., Wu, T., Hanji, P., Banterle, F., Gao, H., Mantiuk, R., & Öztireli, C. (2024) · Computer Graphics Forum · doi:10.1111/cgf.15036 · Cited by 46
“PSNR is more accurate than SSIM and LPIPS NVS methods are typically evaluated using image quality metrics such as PSNR, SSIM, and LPIPS.”
MethodInfluentialShang, Y., Liu, J., Zhang, J., & Wu, Z. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3402058 · Cited by 31
“The reference evaluation metrics consist of spectral angle mapper (SAM), peak signal-to-noise ratio (PSNR), root mse (RMSE), erreur relative globale adimensionnelle de synthèse (ERGAS), and structural similarity (SSIM) [1], [71].”
BackgroundUnderstanding User Experience of Mobile Video: Framework, Measurement, and Optimization
Song, W., Tjondronegoro, D., & Docherty, M. (2012) · InTech eBooks · doi:10.5772/39053 · Cited by 29
“To date, many more effective metrics have been developed, such as structural similarity (SSIM) (Wang, Bovik, Sheikh & Simoncelli, 2004), multiscale SSIM (MS-SSIM) (Wang, Simoncelli & Bovik, 2003), video quality metric (VQM) (Pinson & Wolf, 2004), visual information fidelity (VIF) (Sheikh & Bovik, 2006) and motion-base…”
MethodSeven challenges for image quality research
Chandler, D. M., Alam, M. M., & Phan, T. D. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2047117 · Cited by 27
Progressive compression of arbitrary textured meshes
Caillaud, F., Vidal, V., Dupont, F., et al. (2016) · Computer Graphics Forum · doi:10.1111/cgf.13044 · Cited by 23
“A recent study [LLV16] suggests that perceptual image metrics (in particular the multiscale SSIM [WSB03]) may be good predictors of the visual quality of 3D models.”
BackgroundHyperspectral band selection with objective image quality assessment
Cao, X., Li, X., Li, Z., & Jiao, L. (2017) · International Journal of Remote Sensing · doi:10.1080/01431161.2017.1302110 · Cited by 23
“Second, image distortions, which may or may not depend on the local image statistics, may also be space-variant (Wang et al. 2003).”
BackgroundMethodInfluentialMvSSIM: A quality assessment index for hyperspectral images
Zhu, R., Zhou, F., & Xue, J. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.06.073 · Cited by 23
Visual Quality Assessment of 3D Models
Vanhoey, K., Sauvage, B., Kraemer, P., et al. (2017) · ACM Transactions on Applied Perception · doi:10.1145/3129505 · Cited by 22
Comparison of objective quality models for adaptive bit-streaming services
Lee, C., Woo, S., Baek, S., Han, J., Chae, J., & Rim, J. (2017) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa.2017.8316385 · Cited by 23
“The other four methods (PSNR, SSIM, MS-SSIM, VMAF) is a full-reference method, which requires the corresponding source sequences.”
BackgroundMethodInfluentialHernández-Cabronero, M., Sánchez, V., Blanes, I., Aulí-Llinàs, F., Marcellin, M. W., & Serra-Sagrista, J. S. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2852685 · Cited by 24
“HDR-VDP-2 metric extends [57] and [58] to predict visible differences between two images, and has been shown [39] to provide higher accuracy than other visual metrics such as SSIM, MS-SSIM [60] and mDCT-PSNR [61].”
MethodOverall Quality Prediction for HTTP Adaptive Streaming Using LSTM Network
Tran, H. T. T., Nguyen, D. V., Ngoc, N. P., & Thang, T. C. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3035824 · Cited by 24
Performance Evaluation of Multi-Frame Super-Resolution Algorithms
Nelson, K. J., Bhatti, A., & Nahavandi, S. (2012) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2012.6411669 · Cited by 26
Automated hair removal in dermoscopy images using shallow and deep learning neural architectures
Delibasis, K. K., Μούτσελος, Κ., Vorgiazidou, E., & Maglogiannis, I. G. (2023) · Computer Methods and Programs in Biomedicine Update · doi:10.1016/j.cmpbup.2023.100109 · Cited by 30
Unveiling the Future of Human and Machine Coding: A Survey of End-to-End Learned Image Compression
Huang, C.-H., & Wu, J. (2024) · Entropy · doi:10.3390/e26050357 · Cited by 41
“However, with the resurgence of artificial neural networks, the field of learned image compression has made significant advancements, surpassing the most recent VVC intra-coding performance in terms of PSNR and MS-SSIM [53] metrics on the selected datasets.”
BackgroundGao, X., & Liu, S. (2024) · Remote Sensing · doi:10.3390/rs16173136 · Cited by 27
Zhang, H., Tao, M., Sun, Y., & Letaief, K. B. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3450877 · Cited by 28
“Typically, D data can be measured using metrics such as MSE, multi-scale structural similarity index (MS-SSIM) [34], and learned perceptual image patch similarity (LPIPS) [35] to evaluate the effectiveness of image reconstruction.”
Liu, R. W., Lu, Y., Gao, Y., Guo, Y., Ren, W., Zhu, F., & Wang, F. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3454597 · Cited by 35
“2) Evaluation Metrics: To quantitatively evaluate the visibility enhancement results, we employ the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) [66] as the reference-based evaluation metrics.”
MethodNo-Reference Point Cloud Quality Assessment via Graph Convolutional Network
Wu, C., Jiang, Q., Zhou, W., Shao, F., Zhai, G., & Lin, W. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3521845 · Cited by 28
“The projection-based metrics operate on the projected 2D images of point clouds, including SSIM [56], MS-SSIM [57], IW-SSIM [58], VIFP [59], PQANet [22], and IT-PCQA [24].”
InfluentialSAR Target Recognition With Image Generation and Azimuth Angle Feature Constraints
Xiang, D., Liu, Y., Cheng, J., et al. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3586614 · Cited by 22
“Third, the structural loss, implemented using the multiscale structural similarity (MS-SSIM) [41], [42], emphasizes spatial layout and shape consistency, ensuring that the generated images retain semantic structures under varying azimuth angles.”
Single-Image Super-Resolution Based on Compact KPCA Coding and Kernel Regression
Zhou, F., Yuan, T., Yang, W., et al. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2360038 · Cited by 22
On Box-Cox Transformation for Image Normality and Pattern Classification
Cheddad, A. (2020) · IEEE Access · doi:10.1109/access.2020.3018874 · Cited by 28
“he SSIM and PSNR metrics by incorporating the idea of information content weighted pooling. In this work, we use both extensions; IWPSNR and IWSSIM. - Multi-scale Structural Similarity Index (MSSSIM) [14]: Noticing the dependency of SSIM on image scale, Wang et al. came up with the multi-scale version to circumvent su…”
BackgroundMethodInfluentialL2C – Learning to Learn to Compress
Zou, N., Zhang, H., Cricri, F., Tavakoli, H. R., Lainema, J., Hannuksela, M. M., Aksu, E., & Rahtu, E. (2020) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp48831.2020.9287069 · Cited by 22
“In the first stage, a conventional training session is performed to achieve generalization, by using the following rate-distortion loss: L(x̂, x, z, τ) = λd1Ld1(x̂, x) + λd2Ld2(x̂, x) + λd3Ld3(x̂, x) + λrLr(z) + λmM(τ), (7) where Ld1 is the negative multi-scale structural similarity (MS-SSIM) [25], Ld2 is the mean-squ…”
BackgroundInfluentialChong, Y., Liang, Z., & Pan, S. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3075956 · Cited by 22
“The first is based on the peak signal-to-noise ratio (PSNR) as follows : The other is based on the multiscale structural similarity (MS-SSIM) [48] In the implementation, L MS-SSIM is adopted as the default distortion loss, i.e., we denote our method with L MS-SSIM as HMA (MS-SSIM), while our method…”
MethodFine-Grained Image Quality Assessment: A Revisit and Further Thinking
Zhang, X., Lin, W., & Huang, Q. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3096528 · Cited by 31
Multiple Pose Virtual Try-On Based on 3D Clothing Reconstruction
Tuan, T. T., Minar, M. R., Ahn, H., & Wainwright, J. (2021) · IEEE Access · doi:10.1109/access.2021.3104274 · Cited by 28
Xiao, L., Liu, Y., Yi, Z., Zhao, Y., Xie, L., Cao, P., Leong, A. T. L., & Wu, E. X. (2021) · Magnetic Resonance in Medicine · doi:10.1002/mrm.29033 · Cited by 24
“Note that SSIM can provide a good approximation to perceived image quality given that the human visual system is highly adapted for extracting structural information from images.”
BackgroundMethodBQE-CVP: Blind Quality Evaluator for Colored Point Cloud Based on Visual Perception
Hua, L., Jiang, G., Yu, M., et al. (2021) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb53066.2021.9547070 · Cited by 23
Destroying robust steganography in online social networks
Zhu, Z., Li, S., Qian, Z., et al. (2021) · Information Sciences · doi:10.1016/j.ins.2021.10.023 · Cited by 22
Generator Versus Segmentor: Pseudo-healthy Synthesis
Zhang, Y., Li, C., Lin, X., Sun, L., Zhuang, Y., Huang, Y., Ding, X., Liu, X., & Yu, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87231-1_15 · Cited by 39
“…is expressed as the structural similarity calculated on normal pixels, which is defined as iD = MS-SSIM[(1 − y t ) G ( x p ) , (1 − y t ) (cid:12) x p ], where the (cid:12) denotes the pixel-wise multiplication, and the MS-SSIM() representes a masked Multi-Scale Structural Similarity Index [14].”
Learned Hyperspectral Compression Using a Student’s T Hyperprior
Guo, Y., Chong, Y., Ding, Y., et al. (2021) · Remote Sensing · doi:10.3390/rs13214390 · Cited by 22
Flexible Style Image Super-Resolution Using Conditional Objective
Park, S.-H., Moon, Y. S., & Cho, N. I. (2022) · IEEE Access · doi:10.1109/access.2022.3144406 · Cited by 23
“Figures from 6 to 8 show the performance comparison of 4× SR results according to t, evaluated by the distortion-oriented (PSNR, SSIM [54], MS-SSIM [55]), perception-oriented (LPIPS [56], DISTS [57], VIF [58]), and non-reference perception-oriented metrics (NIQE [59], BRISQUE [60]), respectively.”
MethodPyramid Feature Aggregation for Hierarchical Quality Prediction of Stitched Panoramic Images
Zhou, Y., Gong, W., Sun, Y., Li, L., Wu, J., & Gao, X. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3171684 · Cited by 25
“…is formulated as, where α is a constant between 0 and 1 to represent the relative importance of L ms − ssim and L 1 , L ms − ssim represents the similarity between the restored reference image and the input distorted image, which is calculated using the multiscale SSIM (MS-SSIM) method in [31].”
MethodAW-GAN: face aging and rejuvenation using attention with wavelet GAN
Chandaliya, P. K., & Nain, N. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07721-4 · Cited by 26
“To avoid the denominator begin zero, we set c1 1⁄4 0:0001 and c2 1⁄4 0:0009 followed the reference paper [40].”
MethodBSC-Net: Background Suppression Algorithm for Stray Lights in Star Images
Li, Y., Niu, Z., Sun, Q., Xiao, H., & Li, H. (2022) · Remote Sensing · doi:10.3390/rs14194852 · Cited by 23
Improvement of Urinary Stone Segmentation Using GAN-Based Urinary Stones Inpainting Augmentation
Preedanan, W., Suzuki, K., Kondo, T., Kobayashi, M., Tanaka, H., Ishioka, J., Matsuoka, Y., Fujii, Y., & Kumazawa, I. (2022) · IEEE Access · doi:10.1109/access.2022.3218444 · Cited by 28
“We evaluated the quality of inpainted images using full-reference image quality assessment (FR-IQA) methods including MSE, PSNR, and SSIM [36], as shown in Table 2.”
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.