Blind Prediction of Natural Video Quality
The DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index; none of the 22 sources its claims cite is checked for support yet.
Abstract
We propose a blind (no reference or NR) video quality evaluation model that is nondistortion specific. The approach relies on a spatio-temporal model of video scenes in the discrete cosine transform domain, and on a model that characterizes the type of motion occurring in the scenes, to predict video quality. We use the models to define video statistics and perceptual features that are the basis of a video quality assessment (VQA) algorithm that does not require the presence of a pristine video to compare against in order to predict a perceptual quality score. The contributions of this paper are threefold. 1) We propose a spatio-temporal natural scene statistics (NSS) model for videos. 2) We propose a motion model that quantifies motion coherency in video scenes. 3) We show that the proposed NSS and motion coherency models are appropriate for quality assessment of videos, and we utilize them to design a blind VQA algorithm that correlates highly with human judgments of quality. The proposed algorithm, called video BLIINDS, is tested on the LIVE VQA database and on the EPFL-PoliMi video database and shown to perform close to the level of top performing reduced and full reference VQA algorithms.
Overview
CoChat Summary
TL;DR
The paper proposes Video BLIINDS, a blind/no-reference video quality assessment model based on spatio-temporal natural video statistics in the DCT domain plus motion coherency and global motion features. It predicts perceptual video quality without a pristine reference and performs close to top reduced- and full-reference VQA algorithms on the LIVE VQA and EPFL-PoliMi databases.
Key findings
- Video BLIINDS achieved median SROCC/LCC on the LIVE VQA database of 0.869/0.924 for MPEG-2, 0.839/0.893 for H.264, 0.815/0.951 for wireless, 0.779/0.946 for IP, and 0.759/0.881 when all distortions were mixed.
- It clearly outperformed the blind NIQE index, whose mixed-distortion SROCC/LCC was 0.151/0.317, and also outperformed full-reference PSNR and SSIM; it did not quite reach top full-reference methods such as ST-MAD and MOVIE but was statistically similar to reduced-reference VQM on LIVE.
- In feature-isolation tests, NVS shape-parameter ratios gave the highest prediction SROCC at 0.587, followed by the DC feature at 0.486, spatial naturalness at 0.324, global motion at 0.220, and coherency at 0.204.
- On EPFL-PoliMi, Video BLIINDS achieved median SROCC/LCC of 0.807/0.752 versus NIQE’s 0.555/0.124; on homogeneous EPFL content, its median SROCC rose to 0.989 versus NIQE’s 0.6978.
- Two H.264 applications were demonstrated: bit-rate selection achieved median SROCC 0.954 with median MSE 0.374 MB, and bit-rate prediction achieved median SROCC 0.860 with median MSE 0.471 MB.
Methods
- The model computes frame differences, applies a 5×5 DCT to local patches, fits a generalized Gaussian density to each DCT frequency coefficient, and forms matrices of shape parameters γ per frame difference. It derives low/mid/high spectral ratios from these γ matrices, plus a temporal derivative of mean DC coefficients, motion coherency from a 2D structure tensor on motion vectors, a global motion measure, and NIQE-based spatial naturalness features.
- Features are logarithmically transformed and temporally pooled over 10-second intervals, then used to train a linear kernel support vector regressor for quality prediction.
- Evaluation used the LIVE VQA database (160 videos from 10 reference videos, four distortion types) with content-independent 80%/20% train/test splits over all combinations, reporting SROCC and PLCC; EPFL-PoliMi was also used, with leave-one-out training/testing because it contains only six 4-CIF reference videos.
Limitations
- The paper states that no existing non-distortion-specific blind VQA approaches were available for direct comparison, that blind VQA algorithms trained on a database are applicable to the distortions present in training, and that more complete motion and natural video statistics models are still needed.
- The paper also states that temporal distortion modeling increases computational complexity, that large video corpora are needed for validation, and that its aim is to reach full-reference-level correlations.
- Evident from the text: Video BLIINDS still requires training on human quality scores, does not match top full-reference VQA performance on the mixed LIVE set, and the bit-rate applications assume a particular H.264 encoder parameter configuration.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures























Verification
Claims the paper makes
0 Valid · 2 Not valid · 20 Not checked · 58 Own results and interpretations
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
“It is observed that the parameters of this family differ for pristine and distorted videos.”
plainstates an association- 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.
- Rests on an assumption not shown here.
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
“we utilize them to design a blind VQA algorithm that correlates highly with human judgments of quality.”
plainstates an association- 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.
- Rests on 3 assumptions not shown here.
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 Application 2 (Bit Rate Predictor), a median SROCC of 0 . 860 was achieved between the selected bit rate and the bit rate of the actual compressed videos in the database.”
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.
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 1D generalized Gaussian density is a good fit to these coefficient histograms:”
plainstates an association- 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.
- Rests on an assumption not shown here.
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 Application 1 (Bit Rate Selector), a median SROCC of 0 . 954 was achieved between the predicted and actual bit rates.”
plainstates an association- 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.
44 more claims
Create a free account to see all 80 claims and every source verdict.
- It may state two separate claims as one. 17
- Probably not a substantial claim. 17
- The quote only partly states this claim. 1
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
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
§ B. Model-Based Sub-Band Features: Spectral Ratios · p. 7
“The low frequency band γ 's in each 5 × 5 matrix depicted in Fig. 8 are denoted { γ 12 , γ 13 , γ 21 , γ 22 , γ 23 , γ 31 , γ 32 , γ 33 } .”
§ B. Model-Based Sub-Band Features: Spectral Ratios · p. 7
“The γ -parameters corresponding to the mid-band are notated as { γ 14 , γ 15 , γ 24 , γ 33 , γ 42 , γ 43 , γ 51 , γ 52 }”
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
§ I. INTRODUCTION · p. 2
“and we conclude in Section 6.”
§ IX. CONCLUSION · p. 12
“## IX. CONCLUSION”
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
§ VII. SOME PRACTICAL APPLICATIONS OF VIDEO BLIINDS · p. 12
“Fig. 19. Application 1: Scatter plot of selected versus actual bit rates. <!-- image --> Fig. 20. Application 1: Histogram of SROCC between selected and actual bit rates over 100 iterations of train/test splits.”
§ VII. SOME PRACTICAL APPLICATIONS OF VIDEO BLIINDS · p. 11
“The histogram of the obtained SROCC values is shown in Fig. 20. The median mean square error between predicted and actual bit rates over the 100 iterations was also computed, and it was found to be 0 . 471 MB. A scatter plot of selected versus actual bit rates is further shown in Fig. 19.”
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-citationMaking a “Completely Blind” Image Quality Analyzer
Mittal, A., Soundararajan, R., & Bovik, A. C. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2012.2227726 · Cited by 6,766
Self-citationMultiscale 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-citationImage 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-citationMost apparent distortion: full-reference image quality assessment and the role of strategy
Larson, E. C., & Chandler, D. M. (2010) · Journal of Electronic Imaging · doi:10.1117/1.3267105 · Cited by 1,953
Normalization of cell responses in cat striate cortex
Heeger, D. J. (1992) · Visual Neuroscience · doi:10.1017/s0952523800009640 · Cited by 1,835
kernlab- An S4 Package for Kernel Methods in R
Karatzoglou, A., Smola, A., Hornik, K., & Zeileis, A. (2004) · Journal of Statistical Software · doi:10.18637/jss.v011.i09 · Cited by 1,786
Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality
Moorthy, A. K., & Bovik, A. C. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2147325 · Cited by 1,763
Self-citationBlind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain
Saad, M. A., Bovik, A. C., & Charrier, C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2191563 · Cited by 1,751
Self-citationA new three-step search algorithm for block motion estimation
Li, R., Zeng, B., & Liou, M. L. (1994) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/76.313138 · Cited by 1,536
Research works printed but not linked: 2
- blake, 2006, Perception
- 2007, H 264/MPEG-4 AVC Reference Software Manual
Cited by
Items 401–471 of 471
66‐1: Invited Paper : Trends in Perception of Displayed 3D Stereoscopic Content
Bovik, A. C. (2016) · SID Symposium Digest of Technical Papers · doi:10.1002/sdtp.10838
Self-citationOptimum bit-rate allocation on satellite transponder for best perceptual video quality
Tache, I. (2016) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai.2016.7861067
“PVQ may be affected by overcompression errors, due to the constraints in the bitrate allocation not compatible with the video content.”
Video quality monitoring platform for digital terrestrial television
Tache, I. (2017) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai.2017.8166416
“The non-reference measurement solutions presented in papers such as [3] and [4] can measure only one TV program at a time.”
BackgroundA novel way to calculate PDMOSL based on the coding parameters and network conditions
Du, L., Tian, C., Wu, Z., et al. (2017) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct.2017.8359838
“The classic model of no-reference is VIIDEO [10], which can be used in all scenario, except the application with high real-time requirements.”
Artifact Detection Maps Learned using Shallow Convolutional Networks
Goodall, T., & Bovik, A. C. (2018) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai.2018.8470369
“A variety of state-of-theart picture quality prediction models [1] [2] like BRISQUE [19], NIQE [20], FRIQUEE [21], and Video BLIINDS [22] model the statistical regularities of bandpass natural images and videos, then assess distortions that disturb these regularities.”
BackgroundSelf-citationSpatiotemporal Masking for Objective Video Quality Assessment
He, R., Lu, W. B., Zhang, Y., Gao, X., & He, L. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03398-9_27
No-Reference Video Quality Assessment Based on Ensemble of Knowledge and Data-Driven Models
Su, L., Cosman, P. C., & Peng, Q. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-05716-9_19
Perceptual Image and Video Quality
Ghadiyaram, D., Todd, G., Choi, L. K., & Alan, C. (2018) · doi:10.1201/9781351032742-140000489 · Cited by 1
“Another complementary single-stage approach, BLIINDS-II operates in the DCT domain where a small number of features are computed and yet achieves highly competitive performance.”
MethodNo-Reference Video Quality Assessment (VQA) Using Novel Inter Sub-band 3-D DWT Features
Vishwakarma, A. K., & Bhurchandi, K. M. (2020) · National Conference on Communications · doi:10.1109/ncc48643.2020.9056046
“Also, the same statistical regularities have been observed in a natural video [4, 12].”
BackgroundMethodInfluentialEncoding in the Dark Grand Challenge: an Overview
Anantrasirichai, N., Zhang, F., Malyugina, A., Hill, P., & Katsenou, A. (2020) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew46912.2020.9106011 · Cited by 2
“Since then a variety of different no reference quality metrics have been proposed in the literature, such as the Anisotropic Quality Index (AQI) [40], the Blind Image Quality Index (BIQI) [41], the Contrast Enhancement (CEIQ) employed to measure contrast distortion in [42], the Naturaleness Image Quality Evaluator (NI…”
MethodDeep Local and Global Spatiotemporal Feature Aggregation for Blind Video Quality AssessmentPreprint
Zhou, W., & Chen, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.03411
“As shown in Table 1, the proposed method is compared with 14 state-of-the-art quality assessment metrics, including PSNR, SSIM [4], MS-SSIM [5], FSIM [6], MOVIE [7], ST-MAD [8], ViS3 [3], JVQ [9], VQM [10], STRRED [11], V-CORNIA [12], V-BLIINDS [14], VIIDEO [16], and DeepBVQA [17].”
MethodInfluentialA machine-learning-driven solution to the problem of perceptual video quality metrics
Katsigiannis, S., Rabah, H., & Ramzan, N. (2020) · Institution of Engineering and Technology eBooks · doi:10.1049/pbpc034e_ch12
“…and bitstream information was used by Winkler and Mohandas [12] for real-time video quality estimation, while a combination of a spatio-temporal nat-ural scene statistics (NSS) model for videos and a motion model that quantifies motion coherency in video scenes was proposed by Saad et al. [26].”
MethodThe VIP Gallery for Video Processing EducationPreprint
Goodall, T., & Bovik, A. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.14625 · Cited by 1
“Each frame of input video is scored using SSIM, MOVIE, STRRED, and Video BLIINDS.”
Self-citationPractical Video Quality Assessment Of User Generated Content
Korhonen, J., Wen, X., Cheng, J., & Wang, X. (2021) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew53276.2021.9455974
A No-Reference Perception Based Metric for Detection of Packet Loss Induced Artifacts in Videos
Sanyal, S., & Palit, S. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-92310-5_71
Quality Assessment of In-the-Wild Videos via Multi-Scale Spatio-Temporal Feature Extraction
Liu, S., Li, X., & Zhang, X. (2022) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/iwecai55315.2022.00022
Blind Video Quality Assessment Using Fusion of Novel Structural Features and Deep Features
Vishwakarma, A. K., & Bhurchandi, K. M. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-11349-9_19
Wang, Z., & Lai, L. (2022) · International Conference on Digital Image Processing · doi:10.1117/12.2643807
“Module Input size Output size TDDR (M, T, H, W) (3, 1, H, W) WideResNet50-2 Subnet (3, H, W) (1024, H/16, W/16) Attention-based Pooling (1024, H/16, W/16) (1024, 1) FC (1024) (1)”
BackgroundMethodInfluentialAn integrated functionality framework for robust video streaming heterogeneous networks
Kirubha, D., Easwaramoorthy, S. V., Baiju, B. V., et al. (2023) · Applied and Computational Engineering · doi:10.54254/2755-2721/6/20230850
Zhao, S., Yin, H., Wang, H., & Zhou, Y. (2023) · DCC · doi:10.1109/dcc55655.2023.00008
“For comprehensive comparison, the proposed methods are compared with existing non-reference video quality evaluation methods, including the traditional non-reference quality evaluation methods BRISQUE [12], CORNIA [13], V-BLIIND [14] and the recently proposed VQA methods TLVQM [4], RAPIQUE[15] and CoINVQ [3] for UGC v…”
MethodViewpoint Free Navigation Comfort and Quality Measurement for Windowed 6DoF Synthesized Videos
Jin, C., Luo, T., He, Z., et al. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3365588
“Additionally, among the 15 comparison methods, only four methods exhibit similar performance to the proposed FNC-QM method, namely Video BLIINDS-II [28], 3DSTGabor [29], DoC-DoG-GRNN [36], and Jin et al. [7].”
MethodEnhancing video quality assessment through brightness information
Yuan, J., Peng, Y., & Zhang, A. (2024) · International Conference on Computer Vision and Data Mining (ICCVDM) · doi:10.1117/12.3021606
“Consequently, Video Quality Assessment (VQA) models have gained significant attention from video service providers as they strive to ensure optimal video quality [1, 2, 3].”
BackgroundCombining Deep Learning and Feature Engineering for No-Reference Video Quality Assessment
Decker, A. D., Cock, J. D., & Wallendael, G. V. (2024) · Mile-High Video Conference (MHV) · doi:10.1145/3638036.3640287
Dual Branch Video Quality Evaluation Method
Zhang, L., & Lang, Z. (2023) · International Conference on Electronic Information Engineering and Computer Communication (EIECC) · doi:10.1109/eiecc60864.2023.10456647
Long Term UGC Video Quality Evaluation Based on Transformer
Lang, Z., & Zhang, L. (2024) · International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE) · doi:10.1145/3672758.3672836
“In this section, the method proposed in this paper will be experimentally validated on the selected dataset and compared with recent methods such as NIQE [13] , BRISQUE [14] , CORNIA [15], VBLI-INDS [16], VSFA [1], CNN-TLVQM [17], GSTVQA [3], RAPIQUE [18], HSTVQA [8], BVQA [6], DisCoVQA [19], etc.”
Li, X., & Qiu, J. (2024) · IECE transactions on internet of things. · doi:10.62762/tiot.2024.369369
“Among these, packet loss rate and codec are particularly critical factors impacting video quality [7].”
BackgroundQuality of Experience of Viewport Adaptive Omnidirectional Video Streaming
Liu, X., Zhang, H., Yan, J., Zhang, H., Fang, Y., & Wang, S. (2024) · Proceedings - International Conference on Image Processing · doi:10.1109/icip51287.2024.10647716
Semantic-Aware and Quality-Aware Interaction Network for Blind Video Quality Assessment
Xiang, J., Dang, Y., Chen, P., Liang, R., Huan, R., & Gao, N. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680598 · Cited by 1
“Classic BVQA methods [6, 19, 25, 32, 35, 40] are designed to use hand-crafted features for describing visual quality degradation.”
SCAMS: Semantic Category-Aware Multi-scale Network for Video Quality Assessment
Ren, L., Zhang, K., Fan, D., & Shi, G. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8792-0_26 · Cited by 1
Ultra-high definition video quality assessment method based on deep learning
Li, W., He, C., Zhou, M., Zhang, H., & Liu, W. (2024) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc63484.2024.00095
Multi-Branch Collaborative Learning Network for Video Quality Assessment in Industrial Video Search
Tang, H., Zhang, Z., Li, Z., Zhang, Z., Wu, X., Gao, L. P., Cheng, S., & Yin, D. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709408 · Cited by 2
“Numerous studies have leveraged hand-crafted features to capture quality perception features in videos [17, 28, 35, 41].”
An End-to-End Full-Reference and No-Reference Quality Assessment Model for 360$$^\circ $$ VR Videos
Pei, D., Jia, Z., Sun, W., Duan, H., & Min, X. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4279-3_22
Compression-RQ-VQA: Leveraging Rich Quality-Aware Features for Compressed Video Quality Assessment
Jia, Z., Qian, J., Sun, W., Zhang, Z., Cao, Y., Sun, Y., Zhu, Y., Zhai, G., & Min, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91856-8_5 · Cited by 1
SR-VQA: Super-Resolution Video Quality Assessment Model
Cao, Y., Sun, W., Zhang, W., Sun, Y., Jia, Z., Zhu, Y., Min, X., & Zhai, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91856-8_9 · Cited by 1
Quality Assessment for Talking Head Videos via Multi-Modal Feature Representation
Su, M., Wang, Y., Chen, T., Li, C., Zhao, S., Wen, J., Lin, C., Liu, S., Chu, N., & Zhou, Y. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00130
“In light of the absence of reference videos for the generated TH videos, we only conduct the comparison ex-periment with NR VQA methods, including VIIDEO [33], RAPIQUE [7], V-BLIINDS [34], SimpVQA [6], VSFA [5], FAST-VQA [8], BVQA [35].”
Multi-Dimensional Quality Assessment for UGC Videos via Modular Multi-Modal Vision-Language Models
Zhang, W., Zheng, B., Chen, J., & Wang, Z. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00144 · Cited by 2
“While early VQA models primarily relied on hand-crafted features [19, 23, 26, 46], deep neural networks (DNNs) have emerged as the dominant approach in recent years, owing to their superior representation learning capabilities.”
Xu, L., Zhou, Y., Liu, S., Wen, F., Zhou, Y., Liu, X., Guo, J., Wang, Y., & Cao, J. (2025) · Displays · doi:10.1016/j.displa.2025.103221 · Cited by 1
Ai, D., He, T., Lu, M., Wang, D., & Liu, Y. (2025) · Displays · doi:10.1016/j.displa.2025.103259 · Cited by 3
Yu, R., & Hu, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131834 · Cited by 1
FF-VQA: Frame Replacement and Feature Stitching for Video Quality Assessment
Liao, H.-Y. M., Liu, T.-J., & Liu, K.-H. (2025) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan66881.2025.11207955
JNTD: Toward Just Noticeable Frame Rate-Based Temporal Difference for Perceptual Video Coding
Nami, S., Pakdaman, F., Hashemi, M. R., Shirmohammadi, S., & Gabbouj, M. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3625666 · Cited by 2
ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos
Zhu, X., Duan, H., Yang, L., Zhu, Y., Min, X., Zhai, G., & Callet, P. L. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209505 · Cited by 12
CDHQA: A Quality Assessment Database for Conversational Digital Human
Zhou, Y., Wan, J., Liu, S. W., Xia, Y., Lu, Z., Wen, F., Zhang, Z., Wang, Y., Zhou, Y., Liu, X., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3729-7_2
Exploring Cross-Modal Mutual Prompt Learning for Video Quality Assessment
Chen, P., Li, L., Wu, J., Yan, J., Jakhetiya, V., & Chetouani, A. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3639890 · Cited by 1
“V-BLIINDS [25] also combined features extracted from discrete cosine transform (DCT) domain with the NVS model.”
Wang, Q., Peng, Z., Zou, W., et al. (2025) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3743093.3770975
Subjective and Objective Quality Assessment of Display Content Videos
Huang, Y., Lu, F., Yu, H., Zhang, K., Sun, W., Min, X., & Zhai, G. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3642689
“Furthermore, while traditional NR VQA methods [4], [5], [6] have provided valuable insights, deep learning-based NR VQA models [3], [7], [8], [9], [10], [11], [12], [13] dominate recent advancements.”
EyeSim-VQA: A Free-Energy-Guided Eye Simulation Framework for Video Quality Assessment
Wang, Z., Lu, W. B., Li, J., He, L., Gong, M., & Gao, X. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3651537 · Cited by 1
“V-BLIINDS [41], for example, integrates DCT-domain analysis with the NIQE [16] framework to extract inter-frame variations for quality prediction.”
RAM-VQA: Restoration Assisted Multi-Modality Video Quality Assessment
Chen, P., Yan, J., Soundararajan, R., Valenzise, G., Li, C., & Li, L. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3655117 · Cited by 1
“Subsequent methods extended these principles to the temporal domain: VIIDEO [13] introduced natural video statistics (NVS), while V-BLIINDS [14] combined NVS with DCT-domain features.”
SCCOME: Scene Change Capture and Optical Motion Estimation for Video Quality Assessment
Liu, T.-J., Liao, H.-S., & Liu, K.-H. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343375
“…0.504 0.516 0.365 10.731 NIQE [12] 0.465 0.464 0.328 10.858 CORNIA [13] 0.460 0.494 0.324 10.759 VIIDEO [35] 0.127 -0.0001 0.082 12.308 VBLIINDS [14] 0.566 0.568 0.405 10.760 VSFA [18] 0.737 0.732 0.552 8.863 TLVQM [15] 0.780 0.810 0.595 7.810 VIDEVAL [16] 0.690 0.720 0.511 8.364 RAPIQUE [17]…”
InfluentialLight-VQA+: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidance
Zhou, X., Liu, X., Dong, Y., Kou, T., Gao, Y., Zhang, Z., Li, C., Wu, H., & Zhai, G. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02706-x · Cited by 12
A No-Reference Framework for Animated Video Quality Prediction in Consumer Multimedia Applications
Mogasati, R. S., Ganavdiya, S., Poreddy, A. K. R., Appina, B., & Pachori, R. B. (2026) · IEEE transactions on consumer electronics · doi:10.1109/tce.2026.3671988
“Several research studies [20], [21] have employed the computation of non-overlapping spatiotemporal local patch decomposition for precise spatial and temporal analysis of a video.”
Unveiling the Modular Design of Text-to-Video Quality Assessment
郑炳坤, Zhang, W., Zhai, G., & Yang, X. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3673333 · Cited by 1
“Early BVQA methods rely on natural scene statistics (NSS) features [48], [49], [50], assuming quality correlates with NSS deviations, but such hand-crafted cues struggle to model complex content–distortion interactions.”
Joint Model of Deep Hierarchical Network and Gabor Features via Spatio-Temporal Slice of VideosPreprint
Bediako, D. O., & Nornormey, E. A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6439524
Efficient No-Reference Video Quality Assessment Using Video Masked Autoencoder Feature Mixing
Suresh, N., & Channappayya, S. S. (2025) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf67917.2025.11443711
“V-BLIINDS [10] proposed a spatio-temporal natural scene statistics (NSS) model for videos.”
Liang, Z., Sheng, W., Ma, H., Zhou, F., & Qiu, G. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3679733
“To demonstrate the e ff ectiveness of the proposed model, we compare it with some traditional and state-of-the-art NR VQA models, including V-BLIINDS [51], LVQM [24], VSFA [20], VIDEVAL [25], GSTVQA [21], BVQA [7], FAST-VQA [17], TB-VQA [8], STFEE [16], STI-VQA [48], and HR-VQA [19] on 4K videos.”
Nami, S., Pakdaman, F., Taali, S., et al. (2026) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/3793853.3799805
“…fl uences perceptual masking [4]; Brightness Information (BI), indicating overall luminance levels that a ff ect motion visibility; Motion Coherency (MC), which quanti fi es how coherent motion directions are [17]; and EgoMotion (EM), which quanti fi es global motion arising from camera movement [7].”
Khan, Z. A. (2021) · theses.fr (ABES) · doi:10.70675/75d15fa7z97c5z418cza3b3z8f75630fddaa · Cited by 2
Complexity reduction of VVC video encoding using machine learning techniques
Tissier, A. (2022) · theses.fr (ABES) · doi:10.70675/e00f7223zb09cz4284za197z71526338f2e7
Deep learning-assisted video list decoding in error-prone video transmission systems
Zhang, Y. (2024) · theses.fr (ABES) · doi:10.70675/1d0878eez4905z432az9623zbee74e1a454f
Ganavdiya, S., Mogasati, R. S., Appina, B., et al. (2026) · Displays · doi:10.1016/j.displa.2026.103468
Zhou, Y., Zhang, Z., Wen, F., Xu, L., Zhang, Y., Zhou, Y., Cao, J., Shi, Y., Liu, X., Min, X., et al. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104817
Ge, Q., Min, X., Wu, S., Li, Y., & Zhai, G. (2026) · Sensors · doi:10.3390/s26082530
“Over time, the scope of visual quality assessment has expanded from images to videos and 3D content [19–24].”
InfluentialPerceptual Quality Assessment for Stylized Talking Heads
Wen, F., Zhang, Y., Cao, Y., Zhou, Y., Wang, Z., Xu, Y., 元好, 学., Cao, J., Wang, Y., Zhou, Y., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461498
BrightRate: Quality Assessment for User-Generated HDR Videos
Saini, S., Chen, B., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00154 · Cited by 1
“This combination allows the module to highlight subtle HDR-specific degradations while retaining the interpretability and efficiency of classical statistical features.”
Self-citationVishwakarma, A. K., Ranjan, R., Priyadarshi, R., & Kollie, D. S. (2026) · Discover Computing · doi:10.1007/s10791-026-10248-0 · Cited by 1
“Early handcrafted feature-based models, such as V-BLIINDS [91], TLVQM [98], and VIDEVAL [99], are grounded in the natural scene statistics (NSS) paradigm.”
No-reference video quality assessment with guidance of keyframe extraction
Zhou, M., Han, D., Liu, W., Li, G., Li, M., & Ren, X. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582042
M3DGCQA: A Quality Assessment Dataset for Multi-Object 3D Generated Contents
Wen, F., 元好, 学., Ren, X., Wang, Z., Zhou, Y., Zhang, Z., Jia, J., Shi, Y., Cao, J., Liu, X., et al. (2026) · International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex69967.2026.11618331
“…[48], CPBD [49] and StairIQA [50]; Several mainstream no-reference video quality assessment (NR-VQA) methods are verified, including V-BLIINDS [51], SimpVQA [52], Fast-VQA [53], and BVQA [54]; Two typical no-reference 3D quality assessment (NR-3DQA) methods, including 3D-NSS [55] and MM-PCQA…”
LI-VAD: Lightweight and Interpretable Video Artifact Detection
Palmer, L., Xiao, Z., Li, H., & Kuo, C. J. (2026) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri69576.2026.00107
“MSCN coefficient distributions over frame differences in the DCT domain are grounded in NSS as demonstrated by [13], and we extend this finding with Laws’ filters.”
Yue, G., Liu, T., Dong, L., He, L., Huang, Q., Wang, Z., & Wang, T. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114976
Wang, Q., Peng, Z., Chen, F., et al. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106501
Metadata
- Authors
- Saad, M. A., Bovik, A. C., & Charrier, C.
- Affiliations
- The University of Texas at Austin (US)
- Université de Caen Normandie (FR)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2014-03
- Volume
- 23
- Issue
- 3
- Pages
- 1352-1365
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2048042940
- Cited by
- 471
- References
- 57
- Citations by year
- 2026: 26 · 2025: 47 · 2024: 57 · 2023: 59 · 2022: 48 · 2021: 57 · 2020: 19 · 2019: 30 · 2018: 36 · 2017: 40 · 2016: 21 · 2015: 17 · 2014: 14
- FWCI
- 27.40
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- HAL (submittedVersion)
- 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 › Signal Processing › Video Coding and Compression Technologies
- Keywords
- blind video quality assessment, natural scene statistics, spatio-temporal modeling, discrete cosine transform, motion modeling, perceptual quality
- MeSH terms
- Algorithms, Image Enhancement, Image Interpretation, Computer-Assisted, Motion, Pattern Recognition, Automated, Photography, Sensitivity and Specificity, Video Recording, Reproducibility of Results, Artifacts
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.