Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos
The DOI matches its Crossref record; 91 of the 91 references it cites were found in a registry or an index; 12 of the 89 sources its claims cite were checked for support.
Abstract
There has recently been a great deal of interest in the development of algorithms that objectively measure the integrity of video signals. Since video signals are being delivered to human end users in an increasingly wide array of applications and products, it is important that automatic methods of video quality assessment (VQA) be available that can assist in controlling the quality of video being delivered to this critical audience. Naturally, the quality of motion representation in videos plays an important role in the perception of video quality, yet existing VQA algorithms make little direct use of motion information, thus limiting their effectiveness. We seek to ameliorate this by developing a general, spatio-spectrally localized multiscale framework for evaluating dynamic video fidelity that integrates both spatial and temporal (and spatio-temporal) aspects of distortion assessment. Video quality is evaluated not only in space and time, but also in space-time, by evaluating motion quality along computed motion trajectories. Using this framework, we develop a full reference VQA algorithm for which we coin the term the MOtion-based Video Integrity Evaluation index, or MOVIE index. It is found that the MOVIE index delivers VQA scores that correlate quite closely with human subjective judgment, using the Video Quality Expert Group (VQEG) FRTV Phase 1 database as a test bed. Indeed, the MOVIE index is found to be quite competitive with, and even outperform, algorithms developed and submitted to the VQEG FRTV Phase 1 study, as well as more recent VQA algorithms tested on this database.
Overview
CoChat Summary
TL;DR
The paper develops MOVIE, a full-reference video quality assessment index that integrates spatial and temporal/motion quality using spatio-temporal Gabor decomposition and motion trajectories. On the VQEG FRTV Phase 1 database, MOVIE correlates closely with subjective scores and is competitive with or outperforms several leading VQA algorithms.
Key findings
- On the entire VQEG FRTV Phase 1 database, MOVIE achieved SROCC 0.833, LCC 0.821, and OR 0.644, compared with PSNR SROCC 0.786, Proponent P8 SROCC 0.803, and SSIM with weighting SROCC 0.812.
- On only the 16 natural videos and their distorted versions (256 videos), MOVIE achieved SROCC 0.860, LCC 0.858, OR 0.656, and RMSE 8.093; PSNR had SROCC 0.739 and SSIM without weighting had SROCC 0.802.
- Temporal MOVIE alone outperformed Spatial MOVIE on the entire database (SROCC 0.816 vs. 0.793) and on natural videos (SROCC 0.835 vs. 0.825), and combining both improved over either separately.
- The RMSE between subjective scores and MOVIE scores after nonlinear regression on the entire VQEG database was 8.76; the outlier ratio using the three-sigma rule was 0.488 on the entire database and 0.461 on natural videos.
Methods
- MOVIE is a full-reference VQA framework: reference and test videos are decomposed with a Gabor filterbank; spatial quality uses divisive normalization/contrast masking inspired by SSIM and information-theoretic IQA; temporal quality uses optical flow from the reference via a multi-scale Fleet–Jepson algorithm and motion-tuned weighted Gabor responses; spatial and temporal scores are pooled using coefficient-of-variation frame descriptors and a product.
- Evaluation used the VQEG FRTV Phase 1 database: 20 reference sequences and 16 distorted versions of each, totaling 320 videos; the algorithm ran on one field of interlaced video and ignored color. A separate natural-video analysis used 16 references and 256 videos after omitting 4 animated sources.
- Performance was measured with SROCC, LCC after logistic nonlinear regression, outlier ratio, and RMSE, and compared against PSNR, SSIM variants, and VQEG proponent models.
Limitations
- The paper states that MOVIE ignores color information and uses only one field of interlaced video; color is listed as a future improvement.
- The paper states that temporal pooling is a simple mean of frame-level descriptors, with more advanced temporal pooling left for future work; it also notes that the model is implicitly geared toward natural videos, and 4 animated sequences are omitted from the natural-video table because they contain synthetic properties and text.
- The paper states that evaluation is limited to the VQEG FRTV Phase 1 database, that VQM performance is not reported because VQM was trained on VQEG data, and that some compared algorithms’ reported performance is from the 2000 VQEG study and may have improved since.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures







Verification
Claims the paper makes
10 Valid · 9 Not valid · 43 Not checked · 80 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“This study reveals that cells in V1 that project to MT may be regarded as local motion energy filters that are spatio-temporally separable and tuned to a specific frequency and orientation (such as the Gabor filters used here).”
What the sources say
- Partly supportedcites [35] [35] J. A. Movshon and W. T. Newsome, 'Visual Response Properties of Striate Cortical Neurons Projecting to Area MT in Macaque Monkeys,' Journal Neuroscience , vol. 16, no. 23, pp. 7733-7741, 1996. - sourceExperimental — accuracy not yet measured
The Discussion describes V1 neurons projecting to MT as local motion energy filters responsive within bandpass limits for orientation and spatial and temporal frequency. The spatial and temporal receptive-field results report frequency tuning, but our copy does not establish that these neurons are spatiotemporally separable. (LLM, conf=0.87)
hedged- 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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Further, the responses of several spatio-temporally separable responses can be combined to encode the local speed and direction of motion of the video sequence [57], [58].”
What the sources say
- Not checked — no full text of the sourcecites [57] [57] D. J. Heeger, 'Optical flow using spatiotemporal filters,' Intl. Journal Computer Vision , vol. 1, no. 4, pp. 279-302, 1987. - source
- Partly supportedcites [58] [58] E. P. Simoncelli and D. J. Heeger, 'A model of neuronal responses in visual area MT.' Vision Research , vol. 38, no. 5, pp. 743-761, Mar 1998. - sourceExperimental — accuracy not yet measured
The MT pattern cells section says the model combines responses from V1 cells to produce selectivity for velocity, which includes speed and direction. But the Spatio-temporal frequency tuning section says the model's V1 responses are not spatially and temporally separable; separable tuning is described as a possible alternative, not a feature of the model. (LLM, conf=0.87)
plainstates a cause- 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.
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Translational motion has an easily accessible representation in the frequency domain and these ideas have been used to build motion estimation algorithms for video [8], [57], [58].”
What the sources say
- Not checked — no full text of the sourcecites [8] [8] A. B. Watson and J. Ahumada, A. J., 'Model of human visual-motion sensing,' Journal Optical Society America A: Optics Image Science Vision , vol. 2, no. 2, pp. 322-342, 1985. - source
- Not checked — no full text of the sourcecites [57] [57] D. J. Heeger, 'Optical flow using spatiotemporal filters,' Intl. Journal Computer Vision , vol. 1, no. 4, pp. 279-302, 1987. - source
- Supportedcites [58] [58] E. P. Simoncelli and D. J. Heeger, 'A model of neuronal responses in visual area MT.' Vision Research , vol. 38, no. 5, pp. 743-761, Mar 1998. - source
The MT pattern cells section states that the power spectrum of a translating two-dimensional pattern lies on a plane in the spatio-temporal frequency domain, with the plane’s orientation determined by velocity. The paper uses this representation to explain its model, supporting the attributed claim. (LLM, conf=0.93)
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.
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Our temporal quality computation bears several similarities with the neuronal model of MT in [58], [72]. Similarities include the weighting procedure based on the distance between the linear filters and the motion plane and the normalization of weighted responses.”
What the sources say
- Supportedcites [58] [58] E. P. Simoncelli and D. J. Heeger, 'A model of neuronal responses in visual area MT.' Vision Research , vol. 38, no. 5, pp. 743-761, Mar 1998. - source
The Additional information section says the MT weighting depends on Euclidean distance to the preferred velocity plane. The MT pattern cells section says MT responses are computed from a weighted sum of V1 inputs and then normalized. Together, these support the similarities attributed to this model. (LLM, conf=0.93)
- Not checked — no full text of the sourcecites [72] [72] N. C. Rust, V. Mante, E. P. Simoncelli, and J. A. Movshon, 'How MT cells analyze the motion of visual patterns.' Nature Neuroscience , vol. 9, no. 11, pp. 1421-1431, Nov 2006. - source
plainstates an association- 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.
- Supported
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
“The Root Mean Squared Error (RMSE) between subjective scores and MOVIE scores after non-linear regression on the entire VQEG database is 8.76.”
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.
61 more claims
Create a free account to see all 142 claims and to verify the 2 references still open.
- Probably not a substantial claim. 48
- It may state two separate claims as one. 41
- The quote only partly states this claim. 2
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“One reason frame-by-frame IQA performs less well for VQA is because it ignores temporal information, which is important for video quality due to temporal effects, such as temporal masking and motion perception.3,4”
From ViS3: an algorithm for video quality assessment via analysis of spatial and spatiotemporal slices (2014) · cites this paper as [4]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“Each of these filters has a standard deviation of 2 . 65 pixels along both spatial coordinates and 2 . 65 frames along the temporal axis. In our implementation, the Gabor filters were sampled out to a width of three standard deviations; so the support of the kernels at the finest scale are 15 pixels and 15 frames along the spatial and temporal axes respectively.”
Reported 15 · recomputed 15.9
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-citation(1981) · Cited by 11,963
Multiscale structural similarity for image quality assessment
Wang, Z., Simoncelli, E. P., & Bovik, A. C. (2004) · The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 · doi:10.1109/acssc.2003.1292216 · Cited by 6,253
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-citationComputational modelling of visual attention
Itti, L., & Koch, C. (2001) · Nature Reviews Neuroscience · doi:10.1038/35058500 · Cited by 4,733
Performance of optical flow techniques
Barron, J. L., Fleet, D. J., & Beauchemin, S. S. (1994) · International Journal of Computer Vision · doi:10.1007/bf01420984 · Cited by 4,305
Image information and visual quality
Sheikh, H. R., & Bovik, A. C. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.859378 · Cited by 4,104
Self-citationSpatiotemporal energy models for the perception of motion
Adelson, E. H., & Bergen, J. R. (1985) · Journal of the Optical Society of America A · doi:10.1364/josaa.2.000284 · Cited by 3,442
Relations between the statistics of natural images and the response properties of cortical cells
Field, D. J. (1987) · Journal of the Optical Society of America A · doi:10.1364/josaa.4.002379 · Cited by 3,241
Daugman, J. G. (1985) · Journal of the Optical Society of America A · doi:10.1364/josaa.2.001160 · Cited by 3,219
Research works printed but not linked: 7
- webster, 2008, progress and future plans for vqeg, ETSI STQ Workshop Multimedia Quality of Service
- fox, 1978, Handbook of Sensory Physiology Volume VIII Perception
- lubin, 1993, Digital Images and Human Vision, 163
- seshadrinathan, 2007, an information theoretic video quality metric based on motion models, 1st Int Workshop Video Process Quality Metrics Consum Electron
- girod, 1993, Digital Images and Human Vision, 207
- 0, (2008) NTT News Release
- 2008, Objective Perceptual Multimedia Video Quality Measurement in the Presence of a Full Reference
Cited by
Items 301–400 of 717
Foveation-based content adaptive root mean squared error for video quality assessment
Vranješ, M., Rimac-Drlje, S., & Vranješ, D. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5544-6 · Cited by 10
No-Reference Image Quality Assessment Based on Dual-Domain Feature Fusion
Cui, Y. (2020) · Entropy · doi:10.3390/e22030344 · Cited by 15
EyeQoE: A Novel QoE Assessment Model for 360-degree Videos Using Ocular Behaviors
Zhu, H., Li, T., Wang, C., Jin, W., Murali, S., Xiao, M., Ye, D., & Li, M. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3517240 · Cited by 17
“Existing methods are available to obtain the above information by inspecting I-frames and P-frames in videos [1, 54, 63].”
MethodSpatio-temporal ssim index for video quality assessment
Wang, Y., Jiang, T., Ma, S., & Gao, W. (2012) · Visual Communications and Image Processing · doi:10.1109/vcip.2012.6410779 · Cited by 17
“Considering that HVS is sensitive to edges, motion regions and abruptly emerged artifacts, which usually have high spatial-temporal activities, we judge a pixel is a salient pixel if its spatio-temporal gradient magnitude is above a certain threshold ε in either original video or distorted video.”
BackgroundPerception of differences in naturalistic dynamic scenes, and a V1-based model
To, M. P. S., Gilchrist, I. D., & Tolhurst, D. J. (2015) · Journal of Vision · doi:10.1167/15.1.19 · Cited by 13
“Observers might also compare the frames within each movie clip separately before comparing the two clips, perhaps by coding object movement within the movies, as has been suggested for enhanced measures of video distortion (e.g., Seshadrinathan & Bovik, 2010; Vu & Chandler, 2014; Wang & Li, 2007).”
BackgroundTemporal Video Transcoding Based on Frame Complexity Analysis for Mobile Video Communication
Yeh, C., Jiang, S.-J. F., Lin, C., et al. (2012) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2012.2220414 · Cited by 11
“Visual quality assessment, MOVIE, is also used to evaluate the quality of the transcoded videos; it finds that those of the proposed method have the best perceptual quality.”
MethodInfluentialGarcía, M., Segura-García, J., & Felici-Castell, S. (2017) · Computer Communications · doi:10.1016/j.comcom.2017.08.009 · Cited by 11
Perceptual video quality metric for compression artefacts: from two‐dimensional to omnidirectional
Zou, W., Yang, F., & Wan, S. (2017) · IET Image Processing · doi:10.1049/iet-ipr.2017.0826 · Cited by 11
A Simple Prediction Fusion Improves Data-driven Full-Reference Video Quality Assessment Models
Bampis, C., Bovik, A., & Li, Z. (2018) · Picture Coding Symposium · doi:10.1109/pcs.2018.8456293 · Cited by 14
“Extracting temporal information is important, but in space-time motion-based VQA models such as [2], [8], [10] this leads to computational overheads, e.”
BackgroundMethodResultInfluentialSelf-citationReal-Time Video Super-Resolution with Spatio-Temporal Networks and Motion CompensationPreprint
Caballero, J., Ledig, C., Aitken, A. P., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.05250 · Cited by 11
“The metrics compared are PSNR, structural similarity (SSIM) [40] and MOVIE [31] indices.”
MethodVideo quality degradation on IPTV networks
Okyere-Benya, J., Aldiabat, M., Menkovski, V., et al. (2012) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/iccnc.2012.6167513 · Cited by 10
Machine learning based modeling of spatial and temporal factors for video quality assessment
Narwaria, M., & Lin, W. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6116173 · Cited by 11
Flicker sensitive motion tuned video quality assessment
Choi, L. K., & Bovik, A. C. (2016) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai.2016.7459167 · Cited by 18
“The Gabor filter bank is implemented similar to [5] and [21], but we use a wider range of possible speeds to more accurately measure the spatiotemporal cortical responses of V1 neurons, with filter bandwidths 0.”
BackgroundMethodInfluentialSelf-citationPredicting Spatio-Temporal Entropic Differences for Robust No Reference Video Quality Assessment
Mitra, S., Soundararajan, R., & Channappayya, S. S. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3049682 · Cited by 9
“Considerable progress has been made in designing full reference (FR) VQA algorithms which use a pristine reference video for comparison [1], [2].”
BackgroundWu, W., Hu, S., Xiao, P., Deng, S., Li, J., Chen, Y., & Li, K. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00183 · Cited by 13
“Several researchers have emphasized the importance of considering quality across the temporal axis [15, 31].”
Background360° video quality assessment based on saliency-guided viewport extraction
Yang, F., Yang, C., An, P., & Huang, X. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01285-0 · Cited by 12
Yan, P., Mou, X., & Xue, W. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2083283 · Cited by 13
“Due to the complex temporal effects, such as temporal masking and motion perception, the temporal information [3], [4] has not been efficiently used in VQA algorithms.”
MethodInfluentialVideo quality assessment: A review of full-referenced, reduced-referenced and no-referenced methods
Soong, H.-C., & Lau, P.-Y. (2017) · IEEE International Colloquium on Signal Processing & Its Applications (CSPA) · doi:10.1109/cspa.2017.8064957 · Cited by 10
Video Quality Assessment With Serial Dependence Modeling
Liu, Y., Wu, J., Li, A., Li, L., Dong, W., Shi, G., & Lin, W. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3107148 · Cited by 12
Subjective and objective quality assessment of videos in error-prone network environments
Kim, S., Chae, C., & Lee, J. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2613-6 · Cited by 10
“The velocity and direction of motion of objects in a scene are taken into account [29].”
BackgroundMethodModeling Continuous Video QoE Evolution: A State Space Approach
Eswara, N., Sethuram, H. P., Chakraborty, S., Kuchi, K., Kumar, A., & Channappayya, S. S. (2018) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486557 · Cited by 9
“Many psycho-visual experiments conducted on the visual system suggest that the visual quality and the perceptual experience is highly nonlinear in nature due to nonlinear response properties of the neurons in the primary visual cortex [13].”
BackgroundDeep Video Super-Resolution using HR Optical Flow EstimationPreprint
Wang, L., Guo, Y., Liu, L., Lin, Z., Deng, X., & An, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.02129 · Cited by 10
“To test the consistency performance, we used the temporal motion-based video integrity evaluation index (T-MOVIE) [48].”
MethodObjective video presentation QoE predictor for smart adaptive video streaming
Wang, Z., Zeng, K., Rehman, A., Yeganeh, H., & Wang, S. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2187740 · Cited by 10
“State-of-the-art VQA methods that have been drawing significant attention in recent years include the structural similarity index (SSIM), the multi-scale structural similarity index (MS-SSIM),(8) the video quality metric (VQM)(9) (which is recommended by ITU and adopted by ANSI as a US national standard), and the moti…”
MethodMou, X., & Yan, P. (2018) · Optoelectronic Imaging and Multimedia Technology · doi:10.1117/12.2503149 · Cited by 9
“MOVIE([9]) is a perceptually driven algorithm that uses a three-dimensional Gabor filter bank to filter video in the spatiotemporal domain and then calculates spatial and temporal differences between filtering outputs.”
BackgroundMethodInfluentialLSTM-Based Video Quality Prediction Accounting for Temporal Distortions in Videoconferencing Calls
Mittag, G., Naderi, B., Gopal, V., & Cutler, R. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095711 · Cited by 13
“The MOVIE [13], ST-MAD [14], and STRRED [15] models consider visual perception of motion artifacts.”
MethodStudy of the effects of video content on quality of experience
Paudyal, P., Battisti, F., & Carli, M. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2083223 · Cited by 10
“They can be computed by equation (5) and (6):”
BackgroundVideo Quality Assessment based on Adaptive Block-size Transform Just-Noticeable Difference model
Ma, L., Zhang, F., Li, S., & Ngan, K. N. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5649188 · Cited by 9
“In order to integrate the explicit motion information, MOtion-based Video Integrity Evaluation index (MOVIE) [10] is proposed by tracking perceptually relevant distortions along motion trajectories, thus augmenting the measurement of spatial artifacts in videos.”
MethodA Matlab-Based Tool for Video Quality Evaluation without Reference
Zach, O., & Slanina, M. (2014) · DOAJ (DOAJ: Directory of Open Access Journals) · Cited by 9
Video Quality Model for Space-Time Resolution Adaptation
Lee, D. Y., Ko, H., Kim, J.-H., & Bovik, A. C. (2020) · IEEE International Conference on Image Processing, Applications and Systems (IPAS) · doi:10.1109/ipas50080.2020.9334940 · Cited by 11
“Unlike older Video Quality Assessment (VQA) models that compute optical flow [24, 25] our model does not compute motion vectors, but instead finds space-time paths of maximal statistical regularity.”
BackgroundSelf-citationHierarchical visual comfort assessment for stereoscopic image retargeting
Zhou, Y., Chen, Z., & Li, W. (2021) · Signal Processing Image Communication · doi:10.1016/j.image.2021.116236 · Cited by 9
Measuring and managing picture quality
Bull, D., & Zhang, F. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-820353-8.00019-0 · Cited by 11
Performance-analysis-based acceleration of image quality assessment
Phan, T. D., Sohoni, S., Chandler, D., & Larson, E. (2012) · 2012 IEEE Southwest Symposium on Image Analysis and Interpretation · doi:10.1109/ssiai.2012.6202458 · Cited by 10
HEVC enhancement using content-based local QP selection
Zhang, F., & Bull, D. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7533154 · Cited by 9
“The last two decades have seen the development of numerous perception-based image and video quality assessment methods, which exploit different characteristics of the human visual system (HVS), including: just noticeable distortion (JND) [7, 8] methods [9], contrast sensitivity [10] based quality metrics [11], similar…”
BackgroundAn efficient temporal distortion measure of videos based on spacetime texture
Peng, P., Liao, D., & Li, Z.-N. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.04.031 · Cited by 10
Power of tempospatially unified spectral density for perceptual video quality assessment
Aabed, M. A., Kwon, G., & AlRegib, G. (2017) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2017.8019333 · Cited by 10
“Moreover, we compared our metric with commonly used and state of the art full-reference VQA metrics such as MOVIE [6], VQM [16], MS-SSIM [17], VIF [18], VSNR [19] and NQM [20].”
MethodCNN-MR for No Reference Video Quality Assessment
Wang, C., Su, L., & Huang, Q. (2017) · International Conference on Information Science and Control Engineering · doi:10.1109/icisce.2017.56 · Cited by 9
“Although typical FR algorithms such as STMAD [1], ViS3 [2], MOVIE [3] and RR algorithms like RRED [4] have shown well performance, we can not get enough reference information in many situations.”
MethodKumar, R., Nagpal, D., Naik, V. S., et al. (2022) · ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) · doi:10.1145/3492866.3557734 · Cited by 8
“Seshadrinathan and Bovik [23] stated that any video quality analysis must be weighted based on Spatio-temporal distortion since video quality depends not only on resolution but also on the smoothness of playback.”
BackgroundLuminance decomposition and reconstruction for high dynamic range Video Quality Assessment
Yang, J., Wang, Z., Huang, B., Ai, J., Yang, Y., Xiao, J., & Xiong, Z. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.111011 · Cited by 8
Incorporating visual attention models into video quality metrics
Akamine, W. Y. L., & Farias, M. C. Q. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2039780 · Cited by 10
“The MOVIE metric was proposed by the Laboratory for Image and Video Engineering (LIVE) at The University of Texas at Austin.16 It also has a good performance, but has a very high computational complexity.”
MethodDivisively Normalized Sparse Coding: Toward Perceptual Visual Signal Representation
Zhang, X., Ma, S., Wang, S., Zhang, J., Sun, H., & Gao, W. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2899005 · Cited by 9
“Regarding video quality assessment, the motion-based video integrity evaluation [72], which has been proven to achieve high accuracy of quality prediction, also benefits from the philosophy of DNT.”
Deep Learning and Bidirectional Optical Flow Based Viewport Predictions for 360° Video Coding
Adhuran, J., Kulupana, G., & Fernando, A. (2022) · IEEE Access · doi:10.1109/access.2022.3219861 · Cited by 8
“However, the mean intensity must be removed prior to the computation of the magnitude of the filtered pixels as it can be a bias to the low frequency signal components within the particular window [45].”
BackgroundFoveation-based content Adaptive Structural Similarity index
Rimac-Drlje, S., Martinović, G., & Zovko-Cihlar, B. (2011) · International Conference on Systems, Signals and Image Processing · Cited by 16
Deriving video content type from HEVC bitstream semantics
Nightingale, J., Wang, Q., Grecos, C., & Goma, S. (2014) · Photonics Europe · doi:10.1117/12.2051757 · Cited by 8
Parametric Model for Video Streaming Services With Different Spatial and Temporal Resolutions
Song, J., Yang, F., Zhang, W., & Ma, Z. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3041489 · Cited by 9
Enhancing VMAF through New Feature Integration and Model Combination
Zhang, F., Katsenou, A., Bampis, C. G., Krasula, L., Li, Z., & Bull, D. (2021) · Picture Coding Symposium · doi:10.1109/pcs50896.2021.9477458 · Cited by 12
Spatiotemporal just noticeable difference modeling with heterogeneous temporal visual features
Xing, Y., Yin, H., Zhou, Y., Chen, Y., & Yan, C. C. (2021) · Displays · doi:10.1016/j.displa.2021.102096 · Cited by 8
Multi-viewport based 3D convolutional neural network for 360-degree video quality assessment
Guo, J., Huang, L., & Chien, W.-C. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12073-1 · Cited by 8
“Sinno and Bovik [39] constructed a large-scale video quality assessment database especially for the deep neural networks-based VQA due to its great need for large-scale training data.”
BackgroundSIFT-flow-based color correction for multi-view video
Zeng, H., Ma, K., Wang, C., et al. (2015) · Signal Processing Image Communication · doi:10.1016/j.image.2015.05.008 · Cited by 8
“…similarity metric, denoted as SSIM in [23], feature similarity metrics, denoted as FSIM and FSIM C in [24], and motion-based video integrity evaluation metric, denoted as MOVIE in [25], since these metrics are correlated well with the human visual perception and provide good subjective evaluation.”
BackgroundECVQ and EVVQ video quality databases
Vranješ, M., Rimac-Drlje, S., & Vranješ, D. (2012) · International Symposium ELMAR (ELMAR) · Cited by 10
Acceptability-based QoE Management for User-centric Mobile Video Delivery
We, S., Tjondronegoro, D., & Himawan, I. (2014) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2647868.2654923 · Cited by 8
“As most of the subjective assessment studies follow the methods recommended by ITU [8], the existing QoE models [19, 21, 28, 29], are often indicated by mean opinion score (MOS) (1-5 scales).”
BackgroundModeling motion visual perception for video quality assessment
You, J., Ebrahimi, T., & Perkis, A. (2011) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2072298.2071997 · Cited by 9
“Additionally, two popular video quality metrics were included in our experiments, namely VQM [9] and MOVIE [10].”
MethodEstimation-Theoretic Approach to Delayed Decoding of Predictively Encoded Video Sequences
Han, J., Melkote, V., & Rose, K. H. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2227773 · Cited by 8
Assessment of video naturalness using time-frequency statistics
Mittal, A., Saad, M. A., & Bovik, A. C. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025114 · Cited by 9
Self-citationEvaluation of objective quality metrics for multidimensional video scalability
Cheon, M., & Lee, J. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.12.008 · Cited by 7
Nonintrusive Method Based on Neural Networks for Video Quality of Experience Assessment
Valderrama, D. J. L. B., & Gómez, N. G. (2016) · Advances in Multimedia · doi:10.1155/2016/1730814 · Cited by 8
On Evaluating Perceptual Quality of Online User-Generated Videos
Jang, S., & Lee, J.-S. (2016) · IEEE transactions on multimedia · doi:10.1109/tmm.2016.2581582 · Cited by 8
“distortion (MAD)[4], and visual information fidelity (VIF)[5] are well-known FR quality metrics for images, and motionbased video integrity evaluation (MOVIE)[6] and spatiotempo-”
BackgroundSubjective and objective quality assessment of Mobile Videos with In-Capture distortions
Ghadiyaram, D., Pan, J., Bovik, A. C., Moorthy, A. K., Panda, P., & Yang, K. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952385 · Cited by 12
“Though these databases have tremendously accelerated the development of VQA algorithms [8] [9] [10] [11] [12] [13], they do not model in-capture distortions, such as texture distortions, artifacts due to exposure and lens limitations, focus, and color aberrations .”
BackgroundSelf-citationAn alternating proximal approach for blind video deconvolution
Abboud, F., Chouzenoux, É., Pesquet, J.-C., Chenot, J.-H., & Laborelli, L. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.08.007 · Cited by 10
“The MOVIE indicator, introduced in [43], is a perceptual measure mimicking the human subjective judgment to assess the visual quality of a natural video, the smaller value MOVIE is, the better the video restoration result is.”
BackgroundSegura-García, J., Felici-Castell, S., & García, M. (2018) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2018.01.006 · Cited by 10
An error-based video quality assessment method with temporal information
Loh, W.-T., & Bong, D. B. L. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6107-1 · Cited by 8
“non-IQA based is motion-based video integrity evaluation (MOVIE) [23].”
BackgroundMethodInfluentialEfficient viewport prediction and tiling schemes for 360 degree video streaming
Adhuran, J., & Martini, M. G. (2024) · doi:10.1145/3625468.3653425 · Cited by 7
“While in the context of conventional videos ROI detection and ROI based video coding is a vastly investigated research topic [23, 29, 36], in 360 ◦ videos the identification of the regions of human interest is very challenging because the viewports that represent user observed regions are…”
BackgroundNo-reference Video Quality Assessment Based on Spatio-temporal Perception Feature Fusion
Tan, Y., Kong, G., Duan, X., Long, H., & Wu, Y. J. (2022) · Neural Processing Letters · doi:10.1007/s11063-022-10939-x · Cited by 6
“MOVIE [25], by performing a 3D Gabor decomposition of the video, uses the Gabor coefficients to calculate the quality of the spatial domain to the motion information obtained from the optical flow field, calcu-”
MethodMulti-Modal Learning-Based Blind Video Quality Assessment Metric for Synthesized Views
Jin, C., Peng, Z., Chen, F., Jiang, G., & Yu, M. (2023) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2023.3284411 · Cited by 7
“For instance, MOVIE [12] is a classic FR VQA metric, ST-RRED [13] and its upgraded version SpEED [14] are RR VQA metrics, VIIDEO [15] and V-BLIINDS [16] are classic NR VQA metrics.”
BackgroundNo-reference video quality assessment based on region of interest
Lin, X., Tian, X., & Chen, Y. (2012) · International Conference on Consumer Electronics, Communications and Networks (CECNet) · doi:10.1109/cecnet.2012.6202131 · Cited by 7
Reiter, U., Korhonen, J., & You, J. (2011) · EURASIP Journal on Image and Video Processing · doi:10.1186/1687-5281-2011-8 · Cited by 7
“Wang Z, Bovik AC, Sheikh HR, Simoncelli EP: Image quality assessment: from error visibility to structural similarity.”
BackgroundMethodInfluentialWang, M., Zhang, F., & Agrafiotis, D. K. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7350863 · Cited by 6
A Novel Spatial Pooling Strategy for Image Quality Assessment
Li, Q., Fang, Y., & Xu, J. (2016) · Journal of Computational Science and Technology · doi:10.1007/s11390-016-1623-9 · Cited by 7
“Keywords image quality assessment, spatial pooling, statistical pooling, support vector regression, structural similarity”
BackgroundIn-loop perceptual model-based rate-distortion optimization for HEVC real-time encoder
Hu, Q., Zhou, J. W., Zhang, X., Gao, Z., & Sun, M. (2018) · Journal of Real-Time Image Processing · doi:10.1007/s11554-018-0772-1 · Cited by 8
“In [51, 52], motion information is computed from the optical flow fields of the reference video sequence.”
MethodFull-Reference And No-Reference Quality Assessment For Compressed User-Generated Content Videos
Yang, L., Feng, L., Xu, J., Zhang, T., Liao, Y., & Li, J. (2021) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew53276.2021.9456013 · Cited by 13
Chen, Z., Yang, W., & Yang, J. (2022) · Applied Intelligence · doi:10.1007/s10489-021-02882-6 · Cited by 7
“To measure the overall quality of the video, we utilize MOVIE [41].”
MethodDelving into the Frequency: Temporally Consistent Human Motion Transfer in the Fourier Space
Yang, G., Liu, W., Liu, X., Gu, X., Cao, J., & Li, J. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547781 · Cited by 9
“This observation is consist with the conclusions in [29].”
BackgroundMethodResultInfluential2D NO-REFERENCE VIDEO QUALITY MODEL DEVELOPMENT AND 3D VIDEO TRANSMISSION QUALITY
Brunnstrom, K. E., Sedano, I., Wang, K., Barkowsky, M., Kihl, M., Andrén, B., Callet, P. L., Aurelius, A., Ab, A., & France, I. N. (2012) · Cited by 7
Dumić, E., & Grgić, S. (2013) · International Symposium ELMAR (ELMAR) · Cited by 7
A Full Reference Video Quality Measure based on Motion Differences and Saliency Maps Evaluation
Ortiz-Jaramillo, B., Kumcu, A., Platiša, L., & Philips, W. R. (2014) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0004870607140722 · Cited by 7
Quality assessment methods for perceptual video compression
Zhang, F., & Bull, D. (2013) · 2013 IEEE International Conference on Image Processing · doi:10.1109/icip.2013.6738009 · Cited by 11
“Definitions of these four parameters can be found in [13, 15].”
BackgroundMethodVisually Lossless H.264 Compression of Natural Videos
Mittal, A., Moorthy, A. K., & Bovik, A. C. (2012) · The Computer Journal · doi:10.1093/comjnl/bxs105 · Cited by 8
Self-citationA Robust H.264/AVC Video Watermarking Scheme with Drift Compensation
Jiang, X., Sun, T., Zhou, Y., et al. (2014) · The Scientific World JOURNAL · doi:10.1155/2014/802347 · Cited by 7
“To evaluate the change of video quality before and after being watermark embedded, we introduce four new objective evaluation indicators: (i) NQI: new quality metrics; (ii) VQM: Video Quality Measurement techniques; (iii) SSIM: structural similarity; (iv) MOVIE: motion-based video integrity evaluation [17].”
MethodVideo quality assessment using temporal quality variations and machine learning
Narwaria, M., & Lin, W. (2011) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2011.6011936 · Cited by 9
“Another method proposed in [7] also uses motion information but is computationally expensive since it uses three-dimensional optical flow computation.”
MethodViMSSIM: from image to video quality assessment
Vũ, C. T., & Deshpande, S. (2012) · MoVid '12 · doi:10.1145/2151677.2151679 · Cited by 9
“9GHz and4G RAM computer, MOVIE takes approximately 5 hours to compute thequalityindexofa 10secondvideo(25fps, 768× 432).”
MethodInfluentialSSIM-Based Distortion Estimation for Optimized Video Transmission over Inherently Noisy Channels
Sankisa, A., Pandremmenou, K., Pahalawatta, P. V., Kondi, L. P., & Katsaggelos, A. K. (2016) · International Journal of Multimedia Data Engineering and Management · doi:10.4018/ijmdem.2016070103 · Cited by 7
“A FR video quality model called MOtion-based Video Integrity Evaluation (MOVIE) index is proposed in (Seshadrinathan & Bovik, 2010; Seshadrinathan, Soundarajan, Bovik, & Cormack, 2010).”
MethodHEVC/H.265 vs. VP9 for Full HD and UHD video: Is there any difference in QoE?
Kufa, J., Polák, L., & Kratochvíl, T. (2016) · International Symposium ELMAR · doi:10.1109/elmar.2016.7731753 · Cited by 7
A reduced reference video quality assessment of H.264 and mpeg2 codec based on sharpness metric
Amor, M. B., Larabi, M., Kammoun, F., & Masmoudi, N. (2016) · Journal of the Society for Information Display · doi:10.1002/jsid.517 · Cited by 7
Amor, M. B., Kammoun, F., & Masmoudi, N. (2018) · Computer Standards & Interfaces · doi:10.1016/j.csi.2018.04.003 · Cited by 7
Multi-Feature 360 Video Quality Estimation
Azevedo, R. G. D. A., Birkbeck, N., Janatra, I., Adsumilli, B., & Frossard, P. (2021) · IEEE Open Journal of Circuits and Systems · doi:10.1109/ojcas.2021.3073891 · Cited by 10
“Examples of metrics specifically developed for VQA include VQM [30], MOVIE [36], Vis3 [40], and SSTSGMSD [45].”
MethodConvolutional Block Design for Learned Fractional Downsampling
Chen, L., Bampis, C. G., Li, Z., Chen, C., & Bovik, A. C. (2022) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf56349.2022.10052104 · Cited by 15
“Fortunately, many video quality models [29]–[34] have been proposed in recent years.”
BackgroundSelf-citationPerformance Comparison of High Efficiency Video Coding (HEVC) with H.264 AVC
Ram, C., & Panwar, S. (2017) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2017.58 · Cited by 7
“Comparison of metrics was done in [28], [34], [35], [36], [37] and it has been concluded that MS-SSIM, VQM, and MOVIE are the high performance video quality metrics.”
Convolutional Neural Networks for Video Quality AssessmentPreprint
Giannopoulos, M., Tsagkatakis, G., Blasi, S., Toutounchi, F., Mouchtaris, A., Tsakalides, P., Mrak, M., & Ebroul Izquierdo, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.10117 · Cited by 12
“More complex FR metrics have been proposed, including the Video Quality Metric (VQM) [9] and the Motion-based Video Integrity Evaluation (MOVIE) [10], or the Visual Information Fidelity (VIF) [11].”
MethodBlind 3D Video Stabilization with Spatio-Temporally Varying Motion Blur
Li, H., Wang, W., Wang, X., Yuan, X., & Xu, X. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3686159 · Cited by 7
“Moreover, given that the ideal stabilization result for shaky videos is not unique, employing full-reference quality assessments [34] or no-reference quality assessments [47] to objectively evaluate the performance of video stabilizers remains an unresolved challenge.”
On the performance of modern video coding standards with textured sequences
Papadopoulos, M. A., Agrafiotis, D. K., & Bull, D. (2015) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip.2015.7314196 · Cited by 6
-, M. K. T., Saxena, V., & Gupta, J. (2012) · International Journal of Digital Content Technology and its Applications · doi:10.4156/jdcta.vol6.issue20.61 · Cited by 6
“Due to various processing over visual information, it may get distorted when reaches to end user [1-4].”
BackgroundA new combined PSNR for objective video quality assessment
Shang, X., Wang, G., Zhao, H., Liang, J., Wu, C., & Chang, L. (2017) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2017.8019494 · Cited by 8
“Recently, more effective metrics have been proposed, such as motion-based video integrity evaluation (MOIVE) [7], feature similarity [8], visual saliency-based index [9] and convolution neural network (CNN)-based approaches [10, 11, 12].”
BackgroundEnhancing Temporal Quality Measurements in a Globally Deployed Streaming Video Quality Predictor
Bampis, C. G., Li, Z., & Bovik, A. C. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451275 · Cited by 5
“The MOVIE index [13] captures spatiotemporal aspects of video distortions using a spatio-spectral localized multiscale framework.”
BackgroundMethodInfluentialSelf-citationVideo super-resolution using a hierarchical recurrent multireceptive-field integration network
Pang, S., Chen, Z., & Yin, F. (2021) · Digital Signal Processing · doi:10.1016/j.dsp.2021.103352 · Cited by 7
Bi-RSTU: Bidirectional Recurrent Upsampling Network for Space-Time Video Super-Resolution
Wang, H., Yang, W., Liao, Q., & Zhou, J. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3181458 · Cited by 11
Bediako, D. O., Mou, X., & Suobogbiree, M. (2022) · Signal Image and Video Processing · doi:10.1007/s11760-022-02372-3 · Cited by 7
“[5] presented a framework for video quality through spatiotemporal quality, temporal quality, and spatial quality measurement.”
BackgroundMeasuring and Managing Picture Quality
Bull, D. (2014) · Elsevier eBooks · doi:10.1016/b978-0-12-405906-1.00010-6 · Cited by 7
A two-level sliding-window VBR controller for real-time hierarchical video coding
de-Frutos-López, M., del-Ama-Esteban, Ó., Sanz-Rodríguez, S., et al. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5651371 · Cited by 6
“Furthermore, for each input sequence, the encoded bitstream with μPSNR close to 38 dB, our considered medium quality range, was selected for MOVIE index [10] calculation as an estimation of the subjective distortion.”
MethodMicroarchitectural analysis of image quality assessment algorithms
Phan, T. D., Shah, S. K., Chandler, D. M., & Sohoni, S. (2014) · Journal of Electronic Imaging · doi:10.1117/1.jei.23.1.013030 · Cited by 10
A Study of FR Video Quality Assessment of Real Time Video Stream
Zhang, X., Wu, L., Fang, Y., & Jiang, H. (2012) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2012.030601 · Cited by 7
Zhang, H., Li, F., & Li, N. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3558-0 · Cited by 6
“For example, compared to SSIM, our model can reach 13.6 % improvement at R2, 14.8 % improvement at RMSE, 6.3 % improvement at PLCC, 3.5 % improvement at SROCC when no packet loss occur (Ppl=0) .”
BackgroundMethodInfluential
Metadata
- Authors
- Seshadrinathan, K., & Bovik, A. C.
- Affiliations
- Intel (United States) (US)
- The University of Texas at Austin (US)
- ORCID
- Bovik, A.C.
- Venue
- IEEE Transactions on Image Processing
- Published
- 2010-02
- Volume
- 19
- Issue
- 2
- Pages
- 335-350
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2165222134
- Semantic Scholar
- cac2475bcbb52641ac02e7fe046e808d01e4eaaf
- Cited by
- 708
- References
- 83
- Citations by year
- 2026: 14 · 2025: 16 · 2024: 25 · 2023: 31 · 2022: 43 · 2021: 50 · 2020: 41 · 2019: 41 · 2018: 60 · 2017: 59 · 2016: 52 · 2015: 59 · 2014: 69 · 2013: 43 · 2012: 48
- FWCI
- 38.55
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Signal Processing › Video Coding and Compression Technologies
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- video quality assessment, subjective quality correlation, movement trajectories
- MeSH terms
- Algorithms, Humans, Image Processing, Computer-Assisted, Movement, Video Recording, Visual Perception
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
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).
Cited sources are checked with a language model’s help (gpt-6-sol).
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.