UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
Open accessThe DOI matches its Crossref record; 94 of the 94 references it cites were found in a registry or an index; 10 of the 27 sources its claims cite were checked for support.
Abstract
Recent years have witnessed an explosion of user-generated content (UGC) videos shared and streamed over the Internet, thanks to the evolution of affordable and reliable consumer capture devices, and the tremendous popularity of social media platforms. Accordingly, there is a great need for accurate video quality assessment (VQA) models for UGC/consumer videos to monitor, control, and optimize this vast content. Blind quality prediction of in-the-wild videos is quite challenging, since the quality degradations of UGC videos are unpredictable, complicated, and often commingled. Here we contribute to advancing the UGC-VQA problem by conducting a comprehensive evaluation of leading no-reference/blind VQA (BVQA) features and models on a fixed evaluation architecture, yielding new empirical insights on both subjective video quality studies and objective VQA model design. By employing a feature selection strategy on top of efficient BVQA models, we are able to extract 60 out of 763 statistical features used in existing methods to create a new fusion-based model, which we dub the VIDeo quality EVALuator (VIDEVAL), that effectively balances the trade-off between VQA performance and efficiency. Our experimental results show that VIDEVAL achieves state-of-the-art performance at considerably lower computational cost than other leading models. Our study protocol also defines a reliable benchmark for the UGC-VQA problem, which we believe will facilitate further research on deep learning-based VQA modeling, as well as perceptually-optimized efficient UGC video processing, transcoding, and streaming. To promote reproducible research and public evaluation, an implementation of VIDEVAL has been made available online: https://github.com/vztu/VIDEVAL.
Overview
CoChat Summary
TL;DR
This paper benchmarks blind video quality assessment (BVQA) models on large-scale user-generated content (UGC) video databases and proposes VIDEVAL, a feature-fusion model selected from 60 of 763 statistical features. VIDEVAL achieves state-of-the-art or near-state-of-the-art performance at lower computational cost than leading models, and the study provides a reproducible benchmark for UGC-VQA.
Key findings
- VIDEVAL selected 60 of 763 features and achieved SOTA/near-SOTA on all test sets: All-Combinedc SRCC 0.7960, PLCC 0.7939; KoNViD-1k SRCC 0.7832, PLCC 0.7803; LIVE-VQC SRCC 0.7522, PLCC 0.7514; YouTube-UGC SRCC 0.7787, PLCC 0.7733.
- TLVQM outperformed other BVQA models on LIVE-VQC by a notable margin (SRCC 0.7988, PLCC 0.8025) but underperformed on YouTube-UGC (SRCC 0.6693, PLCC 0.6590); models containing temporal features excelled on LIVE-VQC.
- Completely blind NIQE, ILNIQE, and VIIDEO performed poorly; on All-Combinedc, NIQE had SRCC 0.4622/PLCC 0.4773 and VIIDEO had SRCC 0.1039/PLCC 0.1621.
- Deep CNN baselines transferred well: ResNet-50 on KoNViD-1k had SRCC 0.8018/PLCC 0.8104; ensembling VIDEVAL with deep features improved performance by up to ∼4%, e.g., VIDEVAL+ResNet-50 on All-Combinedc had SRCC 0.8115/PLCC 0.8286.
Methods
- Evaluated leading BVQA/BIQA models on KoNViD-1k (1,200 videos), LIVE-VQC (585), YouTube-UGC (1,380; 1,323 color videos as YouTube-UGCc), and All-Combinedc (3,108) after INLSA MOS calibration; used SVR regression, 80%/20% train-test splits repeated 100 times, and reported SRCC, KRCC, PLCC, and RMSE.
- VIDEVAL was built from an initial 763-dimensional feature set drawn from BRISQUE, GM-LOG, HIGRADE-GRAD, FRIQUEE variants, and TLVQM; feature selection used random forest, linear SVM, and SFFS, choosing SVM importance with k=60 over 100 random splits; spatial features were computed every second frame within 1-second chunks with average and standard deviation pooling, then average pooled across chunks.
- Additional analyses included categorical subsets by resolution, content, and quality; cross-dataset generalization; eleven temporal pooling methods; complexity/runtime comparisons; and ensembling VIDEVAL with deep features.
Limitations
- Paper-stated: MOS standard deviation analysis is not presented because LIVE-VQC does not provide it; YouTube-UGC contains 57 grayscale videos that cause numerical errors for FRIQUEE, so color models were evaluated on a 1,323-video subset; temporal pooling results are only self-consistent and not comparable to prior experiments; not enough samples (8–20) per video were available for statistically meaningful pooling; non-natural/computer-generated content remains hard and lacks sufficiently large UGC-VQA datasets.
- Evident from the text: the benchmark covers three databases and a calibrated composite; categorical subsets for animation (81), screen content (163), and gaming (209) are small; cross-dataset generalization is modest (best SRCC values in Tables IX/X range roughly 0.33–0.70); and the deep models evaluated are mostly image-pretrained or picture-quality models rather than video-trained temporal CNNs.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
7 Valid · 1 Not valid · 9 Not checked · 69 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“These two databases, however, only modeled (camera) capture distortions on small numbers of not very diverse unique contents.”
What the sources say
- Partly supportedcites [12] [12] M. Nuutinen, T. Virtanen, M. Vaahteranoksa, T. Vuori, P. Oittinen, and J. H¨ akkinen, 'CVD2014-a database for evaluating no-reference video quality assessment algorithms,' IEEE Trans. Image Process. , vol. 25, no. 7, pp. 3073-3086, 2016. - sourceExperimental — accuracy not yet measured
Our copy supports the CVD2014 half only in part: the Abstract/Introduction and the repository Description state that CVD2014 models real camera-acquisition distortions ('the videos in the CVD2014 database are captured using 78 different cameras, and the distortions are related to the video acquisition process') on a small content base of 234 videos from five different scenes, and Section II.A notes the sequences had to be 'shot by different cameras and still be as similar as possible'. However, the paper never characterizes its own content as 'not very diverse' — Section II.A instead says the sequences 'were captured from many different scenes' — and it makes no evaluative claim of limited unique content. Nothing in our copy addresses LIVE-Qualcomm at all: Table I lists only LIVE [11] and LIVE Mobile [12], both with compression and transmission-error distortions, not capture distortions, so that half of the sentence finds no support here. (LLM, conf=0.70)
- Not checked — no full text of the sourcecites [13] [13] D. Ghadiyaram, J. Pan, A. C. Bovik, A. K. Moorthy, P. Panda, and K.-C. Yang, 'In-capture mobile video distortions: A study of subjective behavior and objective algorithms,' IEEE Trans. Circuits Syst. Video Technol. , vol. 28, no. 9, pp. 2061-2077, 2017. - source
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.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Indeed, if temporal distortions (like judder) are present, they may severely underperform if the frame quality is high [81].”
What the sources say
- Supportedcites [81] [81] P. C. Madhusudana, X. Yu, N. Birkbeck, Y. Wang, B. Adsumilli, and A. C. Bovik, 'Subjective and objective quality assessment of high frame rate videos,' arXiv preprint arXiv:2007.11634 , 2020. - source
The Table 6 discussion says that when high spatial quality is combined with low temporal quality that a model does not assess, spatial measurements unduly influence its video-quality prediction. It also reports that VMAF fails to capture judder/stutter artifacts. This supports the claim for models that inadequately account for temporal distortions. (LLM, conf=0.91)
hedgedstates a possible 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.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The most probable reason would be that these models were trained on picture quality datasets [64], [70], which contain different types of (strictly spatial) distortions than UGC-VQA databases.”
What the sources say
- Partly supportedcites [64] [64] Z. Ying, H. Niu, P. Gupta, D. Mahajan, D. Ghadiyaram, and A. Bovik, 'From patches to pictures (PaQ-2-PiQ): Mapping the perceptual space of picture quality,' in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) , 2020. - sourceExperimental — accuracy not yet measured
Our copy supports the identification half of the attribution: PaQ-2-PiQ's database is a still-picture quality database whose contents are impaired by 'complex mixtures of highly diverse distortions' (Table 1 caption; Sec. 2 'Image Quality Datasets'; Sec. 3.1 UGC-like picture sampling). What the source does not support is the comparative/explanatory part of the claim: nowhere does our copy contrast these distortion types with those of UGC video (VQA) databases, characterise its distortions as 'strictly spatial' in opposition to temporal video distortions, or offer any account of why a picture-quality-trained model performs poorly on video. Searches for video/temporal-distortion comparisons returned only passing mentions (streaming services, VMAF, 'pictures and videos' in Sec. 5). (LLM, conf=0.70)
- Supportedcites [70] [70] V. Hosu, H. Lin, T. Sziranyi, and D. Saupe, 'Koniq-10k: An ecologically valid database for deep learning of blind image quality assessment,' IEEE Trans. Image Process. , vol. 29, pp. 4041-4056, 2020. - source
The citation identifies a picture-quality dataset, and the Introduction (p. 1) identifies KonIQ-10k as a database of images with quality ratings. The Subjective Image Quality Assessment section (p. 4) lists the image degradations considered in those ratings. The proposed reason for the models’ poor performance is the citing authors’ inference, not a finding attributed to this source. (LLM, conf=0.90)
hedgedstates a possible 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.
- Partly supported
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 empirical results show that a simple aggregation of these known models can achieve state-of-the-art (SOTA) performance.”
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.
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
“Performance results are shown in Table VIII, wherein VIDEVAL still outperformed the other BVQA models on both low and high quality partitions.”
plain- 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.
43 more claims
Create a free account to see all 86 claims and to verify the 6 references still open.
- Probably not a substantial claim. 24
- It may state two separate claims as one. 20
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
§ F. Complexity Analysis and Runtime Comparison · p. 13
“Deep ConvNet features ranked second in dimension (VGG-19 (4,080) and ResNet-50 (2,048)).”
§ A. Evaluation Protocol · p. 8
“The fully-connected layer (4,096-dim) from VGG-19 and average-pooled layer (2,048-dim) from ResNet50 served as deep feature descriptors”
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
§ C. Performance Evaluation on Categorical Subsets · p. 11
“The proposed VIDEVAL model outperformed over all categories, followed by ResNet-50 and FRIQUEE, suggesting that VIDEVAL features are robust quality indicatives across different content categories.”
§ B. Performance on Individual and Combined Datasets · p. 10
“| ResNet-50 | 0.6199 | 0.6676 | 0.2781 | 0.4871 | 0.6378 | 0.6779 |”
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
“| Number of ratings | 136,800 (114 votes/video) | 205,000 (240 votes/video)”
Reported 240 · recomputed 350.42735
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
§ UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content · p. 1
“Our experimental results show that VIDEVAL achieves state-of-theart performance at considerably lower computational cost than other leading models.”
§ F. Complexity Analysis and Runtime Comparison · p. 13
“| TLVQM | MATLAB-CPU | 183.8 | | VIDEVAL | MATLAB-CPU | 305.8 |”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 3×
“To conquer the limits of data scale, they either propose to conduct patch-wise training [62], [63], [66] using global scores, or by pretraining deep nets on ImageNet [67], then fine tuning.”
MethodImage 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 · cited 2×
“Some popular FR-VQA models, including PSNR, SSIM [25], and VMAF [21] have already been successfully and massively deployed to optimize streaming and shared/uploaded video encoding protocols by leading video service providers.”
MethodSelf-citationLIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · cited 1×
“As recommended in [80], we optimized the SVR parameter values (C, γ ) by a grid-search of 10×10 exponentially growing sequences (in our experiments, we used a grid of C = 21, 22, .”
MethodMaking 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 · cited 8×
“before (Figure 10a) and after (Figure 10b) INLSA linear mapping, calibrated by NIQE [53] scores.”
MethodInfluentialSelf-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-citationNo-Reference Image Quality Assessment in the Spatial Domain
Mittal, A., Moorthy, A. K., & Bovik, A. C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2214050 · Cited by 6,064 · cited 7×
“We also avoid using duplicate features in different models, such as the BRISQUE-like features in HIGRADE, and the C-DIIVINE features in V-BLIINDS.”
MethodInfluentialSelf-citationDeep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
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 · cited 1×
“These natural scene statistics (NSS) models predictably deviate in the presence of distortions, thereby characterizing perceived quality degradations [47].”
BackgroundSelf-citationA Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms
Sheikh, H. R., Sabir, M. F., & Bovik, A. C. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881959 · Cited by 2,966 · cited 1×
“Several authors report SOTA performance on legacy synthetic distortion databases [68], [69] or on naturally distorted data-”
BackgroundSelf-citationImageNet: A large-scale hierarchical image database
Deng, J. H., Dong, W. F., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 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/cvprw.2009.5206848 · Cited by 2,714
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 · cited 5×
“We also avoid using duplicate features in different models, such as the BRISQUE-like features in HIGRADE, and the C-DIIVINE features in V-BLIINDS.”
BackgroundMethodInfluentialSelf-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 · cited 2×
“Successful blind picture quality assessment (BIQA) models of this type have been developed in the wavelet (BIQI [44], DIIVINE [35], C-DIIVINE [45]), discrete cosine transform (BLIINDS [46], BLIINDS-II [47]), curvelet [48], and spatial intensity domains (NIQE [49], BRISQUE [36]), and have further been extended to video…”
MethodSelf-citationThe serial position effect of free recall.
Murdock, B. B. (1962) · Journal of Experimental Psychology · doi:10.1037/h0045106 · Cited by 1,717
Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index
Xue, W., Zhang, L., Mou, X., & Bovik, A. C. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2293423 · Cited by 1,697 · cited 2×
“Inspired by the efficacy of standard deviation pooling as first introduced in GMSD [71] and later also used in TLVQM [40], we calculate these spatial features every second frame within each sequentially cut non-overlapping 1-second chunk, then we enrich the feature set by applying average and standard deviation pooling…”
MethodSelf-citationYFCC100M: the new data in multimedia research
Thomee, B., Shamma, D. A., Friedland, G., Elizalde, B., Ni, K., Poland, D., Borth, D., & Li, L.-J. (2016) · Communications of the ACM · doi:10.1145/2812802 · Cited by 1,541
An information fidelity criterion for image quality assessment using natural scene statistics
Sheikh, H. R., Bovik, A. C., & de Veciana, G. (2005) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.859389 · Cited by 1,399 · cited 1×
“VQA models require the availability of an entire pristine source video to measure visual differences between a target signal and a corresponding reference [20]–[22], while RRVQA models only make use of a limited amount of reference information [23], [24].”
BackgroundSelf-citationA Feature-Enriched Completely Blind Image Quality Evaluator
Zhang, L., Zhang, L., & Bovik, A. C. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2426416 · Cited by 1,311 · cited 3×
“These baseline models include NIQE [49], ILNIQE [74], VIIDEO [51], BRISQUE [36], GM-LOG [53], HIGRADE [38], FRIQUEE [39], CORNIA [41], HOSA [57], V-BLIINDS [37], and TLVQM [40].”
MethodSelf-citationConvolutional Neural Networks for No-Reference Image Quality Assessment
Kang, L., Ye, P., Li, Y., & Doermann, D. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.224 · Cited by 1,270
Image database TID2013: Peculiarities, results and perspectives
Ponomarenko, N., Jin, L., Ieremeiev, O., Lukin, V., Egiazarian, K., Astola, J., Vozel, B., Chehdi, K., Carli, M., Battisti, F., et al. (2015) · Signal Processing: Image Communication · doi:10.1016/j.image.2014.10.009 · Cited by 1,241
A Two-Step Framework for Constructing Blind Image Quality Indices
Moorthy, A. K., & Bovik, A. C. (2010) · IEEE Signal Processing Letters · doi:10.1109/lsp.2010.2043888 · Cited by 1,196 · cited 1×
“Successful blind picture quality assessment (BIQA) models of this type have been developed in the wavelet (BIQI [48], DIIVINE [37], C-DIIVINE [49]), discrete cosine transform (BLIINDS [50], BLIINDS-II [51]), curvelet [52], and spatial intensity domains (NIQE [53], BRISQUE [38]), and have further been extended to video…”
MethodSelf-citationStudy of Subjective and Objective Quality Assessment of Video
Seshadrinathan, K., Soundararajan, R., Bovik, A. C., & Cormack, L. K. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2042111 · Cited by 1,160 · cited 18×
“Figure 6 displays the histogram of MOS distributions for the three UGC-VQA databases.”
MethodInfluentialSelf-citationVideo 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 · cited 1×
“tine source video to measure visual differences between a target signal and a corresponding reference [20]–[23], while”
BackgroundSelf-citationThe statistics of natural images
Ruderman, D. (1994) · Network: Computation in Neural Systems · doi:10.1088/0954-898x/5/4/006 · Cited by 941 · cited 1×
“The most popular BVQA algorithms deploy perceptually relevant, low-level features based on simple, yet highly regular parametric bandpass models of good-quality scene statistics [46].”
MethodUnsupervised feature learning framework for no-reference image quality assessment
Ye, P., Kumar, J., Kang, L., & Doermann, D. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247789 · Cited by 785
Massive Online Crowdsourced Study of Subjective and Objective Picture Quality
Ghadiyaram, D., & Bovik, A. C. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2500021 · Cited by 782 · cited 4×
“The FRIQUEE model [39] has been observed to achieve SOTA performance both on UGC/consumer video/picture databases like LIVE-Challenge [14], CVD2014 [12], and KoNViD-1k [10] by leveraging a bag of NSS features drawn from diverse color spaces and perceptually motivated transform domains.”
BackgroundMethodInfluentialSelf-citationKonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment
Hosu, V., Lin, H., Sziranyi, T., & Saupe, D. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2967829 · Cited by 759 · cited 3×
“The most probable reason would be that these models were trained on picture quality datasets [64], [70], which contain different types of”
BackgroundMethodMeasuring colorfulness in natural images
Hasler, D., & Suesstrunk, S. E. (2003) · SPIE Proceedings · doi:10.1117/12.477378 · Cited by 729 · cited 1×
“Here we expand the set of attributes to include six low-level features including brightness, contrast, colorfulness [17], sharpness, spatial information (SI), and temporal information (TI), thereby providing a larger visual space in which to plot and analyze content diversities of the three”
BackgroundBlind Image Quality Assessment Using Joint Statistics of Gradient Magnitude and Laplacian Features
Xue, W., Mou, X., Zhang, L., Bovik, A. C., & Feng, X. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2355716 · Cited by 641 · cited 5×
“baseline models include NIQE [53], ILNIQE [78], VIIDEO [55], BRISQUE [38], GM-LOG [57], HIGRADE [40], FRIQUEE [41], CORNIA [43], HOSA [61], KonCept512 [70], PaQ-2-PiQ [64], V-BLIINDS [39], and TLVQM [42].”
BackgroundMethodInfluentialSelf-citationA no-reference perceptual blur metric
Marziliano, P., Dufaux, F., Winkler, S., & Ebrahimi, T. (2003) · Proceedings. International Conference on Image Processing · doi:10.1109/icip.2002.1038902 · Cited by 557 · cited 1×
“Almost all of the earliest BVQA models have been ‘distortion specific,’ meaning they were designed to quantify a specific type of distortion such as blockiness [27], blur [28], ringing [29], banding [30]–[32], or noise [33], [34] in distorted videos, or to assess multiple specific coincident distortion types caused by…”
BackgroundBlind Image Quality Assessment Based on High Order Statistics Aggregation
Xu, J., Ye, P., Li, Q., Du, H., Liu, Y., & Doermann, D. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2585880 · Cited by 495 · cited 7×
“baseline models include NIQE [53], ILNIQE [78], VIIDEO [55], BRISQUE [38], GM-LOG [57], HIGRADE [40], FRIQUEE [41], CORNIA [43], HOSA [61], KonCept512 [70], PaQ-2-PiQ [64], V-BLIINDS [39], and TLVQM [42].”
MethodInfluentialBlind Prediction of Natural Video Quality
Saad, M. A., Bovik, A. C., & Charrier, C. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2299154 · Cited by 471
Self-citationReduced-reference image quality assessment using a wavelet-domain natural image statistic model
Wang, Z., & Simoncelli, E. P. (2005) · SPIE Proceedings · doi:10.1117/12.597306 · Cited by 438
Blind measurement of blocking artifacts in images
Wang, Z., Bovik, A. C., & Evan, B. L. (2002) · Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101) · doi:10.1109/icip.2000.899622 · Cited by 413
Self-citationFrom Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality
Ying, Z., Niu, H., Gupta, P., Mahajan, D., Ghadiyaram, D., & Bovik, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00363 · Cited by 406
Self-citationQuality Assessment of In-the-Wild Videos
Li, D., Jiang, T., & Jiang, M. (2019) · Proceedings of the 27th ACM International Conference on Multimedia · doi:10.1145/3343031.3351028 · Cited by 387 · cited 1×
“nnected layers to predict video quality. Zhang [69] leveraged transfer learning to develope a general-purpose BVQA framework based on weakly supervised learning and a resampling strategy. In the VSFA [70] model, the authors applied a pre-trained image classification CNN as a deep feature extractor and integrated the fr…”
MethodA DCT Statistics-Based Blind Image Quality Index
Saad, M. A., Bovik, A. C., & Charrier, C. (2010) · IEEE Signal Processing Letters · doi:10.1109/lsp.2010.2045550 · Cited by 372 · cited 1×
“Successful blind picture quality assessment (BIQA) models of this type have been developed in the wavelet (BIQI [48], DIIVINE [37], C-DIIVINE [49]), discrete cosine transform (BLIINDS [50], BLIINDS-II [51]), curvelet [52], and spatial intensity domains (NIQE [53], BRISQUE [38]), and have further been extended to video…”
MethodSelf-citationVideo Quality Assessment by Reduced Reference Spatio-Temporal Entropic Differencing
Soundararajan, R., & Bovik, A. C. (2013) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2012.2214933 · Cited by 368 · cited 1×
“RR-VQA models only make use of a limited amount of reference information [24], [25].”
MethodSelf-citationA Completely Blind Video Integrity Oracle
Mittal, A., Saad, M. A., & Bovik, A. C. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2502725 · Cited by 357 · cited 4×
“Among these, NIQE, IL-NIQE, and VIIDEO are “completely blind” (opinion-unaware (OU)), since no training is required to build them.”
MethodInfluentialSelf-citationTwo-Level Approach for No-Reference Consumer Video Quality Assessment
Korhonen, J. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2923051 · Cited by 354 · cited 18×
“Some motion-related features (as in TLVQM) may not apply as well in this scenario.”
BackgroundMethodInfluentialThe Konstanz natural video database (KoNViD-1k)
Hosu, V., Hahn, F., Jenadeleh, M., Lin, H., Men, H., Sziranyi, T., Li, S., & Saupe, D. (2017) · 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex.2017.7965673 · Cited by 343 · cited 9×
“[10] by leveraging a bag of NSS features drawn from diverse”
BackgroundMethodInfluentialVisual Importance Pooling for Image Quality Assessment
Moorthy, A. K., & Bovik, A. C. (2009) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2009.2015374 · Cited by 340 · cited 1×
“A total of eleven pooling methods were tested: three Pythagorean means (arithmetic, geometric, and harmonic mean), median, Minkowski (p = 2) mean, percentile pooling (20%) [84], VQPooling [82], primacy and recency pooling [85], hysteresis pooling [60], and our previously proposed”
MethodSelf-citationPerceptual quality prediction on authentically distorted images using a bag of features approach
Ghadiyaram, D., & Bovik, A. C. (2017) · Journal of Vision · doi:10.1167/17.1.32 · Cited by 322 · cited 11×
“baseline models include NIQE [53], ILNIQE [78], VIIDEO [55], BRISQUE [38], GM-LOG [57], HIGRADE [40], FRIQUEE [41], CORNIA [43], HOSA [61], KonCept512 [70], PaQ-2-PiQ [64], V-BLIINDS [39], and TLVQM [42].”
MethodInfluentialSelf-citationMCL-JCV: A JND-based H.264/AVC video quality assessment dataset
Wang, H., Gan, W., Hu, S., Lin, J. Y., Jin, L., Song, L., Wang, P., Katsavounidis, I., Aaron, A., & Kuo, C.-C. J. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7532610 · Cited by 319 · cited 1×
“Other similar databases targeting simulated compression and transmission distortions have been released subsequently, including EPFL-PoliMI [2], VQEG-HDTV [3], IVP [4], TUM 1080p50 [5], CSIQ [6], MCL-V [7], and MCL-JCV [8].”
MethodLarge-Scale Study of Perceptual Video Quality
Sinno, Z., & Bovik, A. C. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2869673 · Cited by 310 · cited 4×
“PUBLIC LARGE-SCALE USER-GENERATED CONTENT VIDEO QUALITY ASSESSMENT (UGC-VQA) DATABASES COMPARED: KONVID-1K [10], LIVE-VQC [9], AND YOUTUBE-UGC [11]”
BackgroundMethodInfluentialSelf-citationAnalysis of Public Image and Video Databases for Quality Assessment
Winkler, S. (2012) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2012.2215007 · Cited by 299 · cited 3×
“As a way of characterizing the content diversity of the videos in each database, Winkler [16] suggested three quanti-”
MethodInfluentialKim, J., Zeng, H., Ghadiyaram, D., Lee, S., Zhang, L., & Bovik, A. C. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2736018 · Cited by 283 · cited 4×
“To conquer the limits of data scale, they either propose to conduct patch-wise training [62], [63], [66] using global scores, or by pretraining deep nets on ImageNet [67], then fine tuning.”
MethodInfluentialSelf-citationYouTube UGC Dataset for Video Compression Research
Wang, Y., Inguva, S., & Adsumilli, B. (2019) · 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2019.8901772 · Cited by 282 · cited 4×
“PUBLIC LARGE-SCALE USER-GENERATED CONTENT VIDEO QUALITY ASSESSMENT (UGC-VQA) DATABASES COMPARED: KONVID-1K [10], LIVE-VQC [9], AND YOUTUBE-UGC [11]”
BackgroundMethodInfluentialSelf-citationCVD2014—A Database for Evaluating No-Reference Video Quality Assessment Algorithms
Nuutinen, M., Virtanen, T., Vaahteranoksa, M., Vuori, T., Oittinen, P., & Hakkinen, J. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2562513 · Cited by 227 · cited 8×
“(CVD2014) [12], which consists of videos with in-the-wild distortions from 78 different video capture devices, followed by the similar LIVE-Qualcomm Mobile In-Capture Database [13].”
BackgroundMethodInfluentialA deep neural network for image quality assessment
Bosse, S., Maniry, D., Wiegand, T., & Samek, W. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7533065 · Cited by 223 · cited 1×
“To conquer the limits of data scale, they either propose to conduct patch-wise training [62], [63], [66] using global scores, or by pretraining deep nets on ImageNet [67], then fine tuning.”
MethodRAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content
Tu, Z., Yu, X., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2021.3090333 · Cited by 215
Self-citationViS3: an algorithm for video quality assessment via analysis of spatial and spatiotemporal slices
Vu, P. V., & Chandler, D. M. (2014) · Journal of Electronic Imaging · doi:10.1117/1.jei.23.1.013016 · Cited by 185 · cited 2×
“These SOTA deep CNN-based BVQA models [71]–[74] produce accurate quality predictions on legacy (single synthetic distortion) video datasets [1], [6], but”
MethodNo-Reference Quality Assessment of Tone-Mapped HDR Pictures
Kundu, D., Ghadiyaram, D., Bovik, A. C., & Evans, B. L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2685941 · Cited by 182 · cited 7×
“We also avoid using duplicate features in different models, such as the BRISQUE-like features in HIGRADE, and the C-DIIVINE features in V-BLIINDS.”
BackgroundMethodInfluentialSelf-citationFast and reliable structure-oriented video noise estimation
Amer, A., & Dubois, E. (2005) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2004.837017 · Cited by 178
No-reference image quality assessment in curvelet domain
Liu, L., Dong, H., Huang, H., & Bovik, A. C. (2014) · Signal Processing: Image Communication · doi:10.1016/j.image.2014.02.004 · Cited by 177 · cited 1×
“Successful blind picture quality assessment (BIQA) models of this type have been developed in the wavelet (BIQI [48], DIIVINE [37], C-DIIVINE [49]), discrete cosine transform (BLIINDS [50], BLIINDS-II [51]), curvelet [52], and spatial intensity domains (NIQE [53], BRISQUE [38]), and have further been extended to video…”
MethodSelf-citationSpatiotemporal Statistics for Video Quality Assessment
Li, X., Guo, Q., & Lu, X. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2568752 · Cited by 176 · cited 1×
“Successful blind picture quality assessment (BIQA) models of this type have been developed in the wavelet (BIQI [48], DIIVINE [37], C-DIIVINE [49]), discrete cosine transform (BLIINDS [50], BLIINDS-II [51]), curvelet [52], and spatial intensity domains (NIQE [53], BRISQUE [38]), and have further been extended to video…”
MethodImage information and visual quality
Sheikh, H. R., & Bovik, A. C. (2004) · 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.2004.1326643 · Cited by 164
Self-citationIn-Capture Mobile Video Distortions: A Study of Subjective Behavior and Objective Algorithms
Ghadiyaram, D., Pan, J., Bovik, A. C., Moorthy, A. K., Panda, P., & Yang, K.-C. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2707479 · Cited by 154 · cited 6×
“In the VSFA model [74], the authors applied a pre-trained image classification CNN as a deep feature extractor and integrated the frame-wise deep features using a gated recurrent unit and a subjectively-inspired temporal pooling layer, and reported leading performance on several natural video databases [10], [12], [13…”
BackgroundMethodInfluentialSelf-citationKim, W., Kim, J., Ahn, S., Kim, J., & Lee, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01246-5_14 · Cited by 143
Temporal hysteresis model of time varying subjective video quality
Seshadrinathan, K., & Bovik, A. C. (2011) · 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2011.5946613 · Cited by 135 · cited 3×
“Temporal pooling is one of the most important, unresolved problems for video quality prediction [42], [60], [76], [82], [83].”
BackgroundMethodSelf-citationImage Quality Assessment Using Human Visual DOG Model Fused With Random Forest
Pei, S.-C., & Chen, L.-H. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2440172 · Cited by 132
No-reference image quality assessment based on log-derivative statistics of natural scenes
Zhang, Y., & Chandler, D. M. (2013) · Journal of Electronic Imaging · doi:10.1117/1.jei.22.4.043025 · Cited by 128 · cited 1×
“the gradient magnitude and Laplacian of Gaussian responses in the spatial domain (GM-LOG [57]), in log-derivative and log-Gabor spaces (DESIQUE [58]), as well as in the gradient domain of LAB color transforms (HIGRADE [40]).”
BackgroundEnd-to-End Blind Quality Assessment of Compressed Videos Using Deep Neural Networks
Liu, W., Duanmu, Z., & Wang, Z. (2018) · Proceedings of the 26th ACM international conference on Multimedia · doi:10.1145/3240508.3240643 · Cited by 122 · cited 1×
“The V-MEON model [72] used a multi-task CNN framework which jointly optimizes a 3D-CNN for feature extraction and a codec classifier using fully-connected layers to predict video quality.”
MethodVideo quality assessment using structural distortion measurement
Wang, Z., Lu, L., & Bovik, A. C. (2003) · Proceedings. International Conference on Image Processing · doi:10.1109/icip.2002.1038904 · Cited by 122
Self-citationA H.264/AVC video database for the evaluation of quality metrics
De Simone, F., Tagliasacchi, M., Naccari, M., Tubaro, S., & Ebrahimi, T. (2010) · 2010 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2010.5496296 · Cited by 120 · cited 1×
“Other similar databases targeting simulated compression and transmission distortions have been released subsequently, including EPFL-PoliMI [2], VQEG-HDTV [3], IVP [4], TUM 1080p50 [5], CSIQ [6], MCL-V [7], and MCL-JCV [8].”
MethodVideo Quality Pooling Adaptive to Perceptual Distortion Severity
Park, J., Seshadrinathan, K., Lee, S., & Bovik, A. C. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2219551 · Cited by 119 · cited 2×
“Temporal pooling is one of the most important, unresolved problems for video quality prediction [42], [60], [76], [82], [83].”
BackgroundMethodSelf-citationMCL-V: A streaming video quality assessment database
Lin, J. Y., Song, R., Wu, C.-H., Liu, T., Wang, H., & Kuo, C.-C. J. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.02.012 · Cited by 106 · cited 1×
“Other similar databases targeting simulated compression and transmission distortions have been released subsequently, including EPFL-PoliMI [2], VQEG-HDTV [3], IVP [4], TUM 1080p50 [5], CSIQ [6], MCL-V [7], and MCL-JCV [8].”
MethodZhang, Y., Moorthy, A. K., Chandler, D. M., & Bovik, A. C. (2014) · Signal Processing: Image Communication · doi:10.1016/j.image.2014.05.004 · Cited by 102
Self-citationBlind Video Quality Assessment With Weakly Supervised Learning and Resampling Strategy
Zhang, Y., Gao, X., He, L., Lu, W. B., & He, R. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2868063 · Cited by 86 · cited 1×
“Zhang [73] leveraged transfer learning to develop a general-purpose BVQA framework based on weakly supervised learning and a resampling strategy.”
BackgroundNo-reference video quality assessment via feature learning
Xu, J., Ye, P., Liu, Y., & Doermann, D. (2014) · 2014 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2014.7025098 · Cited by 85 · cited 7×
“As may be seen, codebook-based algorithms (CORNIA (10 k ) and HOSA (14.7 k )) require significantly larger numbers of features than other hand-crafted feature based models.”
MethodInfluentialRecurrent and Dynamic Models for Predicting Streaming Video Quality of Experience
Bampis, C. G., Li, Z., Katsavounidis, I., & Bovik, A. C. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2815842 · Cited by 84 · cited 1×
“Temporal pooling is one of the most important, unresolved problems for video quality prediction [42], [60], [76], [82], [83].”
BackgroundSelf-citationProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression
Chen, L.-H., Bampis, C. G., Li, Z., Norkin, A., & Bovik, A. C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3036752 · Cited by 79 · cited 1×
“For example, several deep learning picture-quality prediction methods were proposed in [62]–[65].”
BackgroundSelf-citationA Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment
Tu, Z., Chen, C.-J., Chen, L.-H., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2020) · 2020 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip40778.2020.9191169 · Cited by 71 · cited 9×
“In our previous work [76], we have studied the efficacy”
BackgroundMethodResultInfluentialSelf-citationYFCC100M: The New Data in Multimedia Research
Thomee, B., Shamma, D. A., Friedland, G., Elizalde, B., Ni, K., Poland, D., Borth, D., & Li, L.-J. (2015) · arXiv · doi:10.48550/arxiv.1503.01817 · Cited by 69
Subjective and Objective Quality Assessment of High Frame Rate Videos
Madhusudana, P. C., Yu, X., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2020) · arXiv · doi:10.48550/arxiv.2007.11634 · Cited by 69
Self-citationSubjective and Objective Quality Assessment of High Frame Rate Videos
Madhusudana, P. C., Yu, X., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Access · doi:10.1109/access.2021.3100462 · Cited by 65
Self-citationMeasurement of ringing artifacts in JPEG images
Feng, X., & Allebach, J. P. (2006) · SPIE Proceedings · doi:10.1117/12.645089 · Cited by 56 · cited 1×
“Almost all of the earliest BVQA models have been ‘distortion specific,’ meaning they were designed to quantify a specific type of distortion such as blockiness [27], blur [28], ringing [29], banding [30]–[32], or noise [33], [34] in distorted videos, or to assess multiple specific coincident distortion types caused by…”
BackgroundAn objective method for combining multiple subjective data sets
Pinson, M., & Wolf, S. (2003) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.509909 · Cited by 49
BBAND INDEX: A NO-REFERENCE BANDING ARTIFACT PREDICTOR
Tu, Z., Lin, J., Wang, Y., Adsumilli, B., & Bovik, A. C. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053634 · Cited by 46 · cited 1×
“…specific,’ meaning they were designed to quantify a specific type of distortion such as blockiness [26], blur [27], ringing [28], banding [29], [30], or noise [31], [32] in distorted videos, or to assess multiple specific coincident distortion types caused by compression or transmission…”
BackgroundSelf-citationZhang, Y., & Chandler, D. M. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2001342 · Cited by 45
The TUM high definition video datasets
Keimel, C., Redl, A., & Diepold, K. (2012) · 2012 Fourth International Workshop on Quality of Multimedia Experience · doi:10.1109/qomex.2012.6263865 · Cited by 40 · cited 3×
“In order to study overall model performances on all the databases, we created a large composite benchmark, which is referred to here as All-Combinedc, using the iterative nested least squares algorithm (INLSA) suggested in [77], wherein YouTube-UGC is selected as the anchor set, and the objective MOS from the other tw…”
MethodFilm Grain Synthesis for AV1 Video Codec
Norkin, A., & Birkbeck, N. (2018) · 2018 Data Compression Conference · doi:10.1109/dcc.2018.00008 · Cited by 38 · cited 1×
“Almost all of the earliest BVQA models have been ‘distortion specific,’ meaning they were designed to quantify a specific type of distortion such as blockiness [27], blur [28], ringing [29], banding [30]–[32], or noise [33], [34] in distorted videos, or to assess multiple specific coincident distortion types caused by…”
BackgroundSelf-citationA perceptual visibility metric for banding artifacts
Wang, Y., Kum, S.-U., Chen, C., & Kokaram, A. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7532722 · Cited by 36 · cited 1×
“Almost all of the earliest BVQA models have been ‘distortion specific,’ meaning they were designed to quantify a specific type of distortion such as blockiness [27], blur [28], ringing [29], banding [30]–[32], or noise [33], [34] in distorted videos, or to assess multiple specific coincident distortion types caused by…”
BackgroundSelf-citationNo-reference video quality evaluation for high-definition video
Keimel, C., Oelbaum, T., & Diepold, K. J. (2009) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2009.4959791 · Cited by 33 · cited 1×
“Almost all of the earliest BVQA models have been ‘distortion specific,’ meaning they were designed to quantify a specific type of distortion such as blockiness [27], blur [28], ringing [29], banding [30]–[32], or noise [33], [34] in distorted videos, or to assess multiple specific coincident distortion types caused by…”
BackgroundTu, Z., Lin, J., Wang, Y., Adsumilli, B., & Bovik, A. C. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.3024985 · Cited by 31 · cited 1×
“Almost all of the earliest BVQA models have been ‘distortion specific,’ meaning they were designed to quantify a specific type of distortion such as blockiness [27], blur [28], ringing [29], banding [30]–[32], or noise [33], [34] in distorted videos, or to assess multiple specific coincident distortion types caused by…”
BackgroundSelf-citationPerceptual Video Quality Prediction Emphasizing Chroma Distortions
Chen, L.-H., Bampis, C. G., Li, Z., Sole, J., & Bovik, A. C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3043127 · Cited by 29
Self-citationLarge Scale Subjective Video Quality Study
Sinno, Z., & Bovik, A. C. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451467 · Cited by 24
Self-citationSpatio-Temporal Measures Of Naturalness
Sinno, Z., & Bovik, A. C. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803115 · Cited by 16 · cited 1×
“Successful blind picture quality assessment (BIQA) models of this type have been developed in the wavelet (BIQI [48], DIIVINE [37], C-DIIVINE [49]), discrete cosine transform (BLIINDS [50], BLIINDS-II [51]), curvelet [52], and spatial intensity domains (NIQE [53], BRISQUE [38]), and have further been extended to video…”
MethodSelf-citationNo-Reference Quality Metric for Degraded and Enhanced Video
Caviedes, J. E., & Oberti, F. (2017) · CRC Press eBooks · doi:10.1201/9781420027822-10 · Cited by 8
Perceptual Video Quality Prediction Emphasizing Chroma Distortions
Chen, L.-H., Bampis, C. G., Li, Z., et al. (2020) · arXiv · doi:10.48550/arxiv.2009.11203
RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content
Tu, Z., Yu, X., Wang, Y., et al. (2021) · arXiv · doi:10.48550/arxiv.2101.10955
Self-citationReliable and fast structure-oriented video noise estimation
Amer, A., Mitiche, A., & Dubois, E. (n.d.) · Proceedings. International Conference on Image Processing · doi:10.1109/icip.2002.1038156
No-reference document image quality assessment based on high order image statistics
Xu, J., Ye, P., Li, Q., et al. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7532968
Research works printed but not linked: 4
- li, 2016, Toward A Practical Perceptual Video Quality Metric
- van der maaten, 2008, Visualizing data using t-SNE, J Mach Learn Res, 9, 2579
- zhang, 2011, IVP subjective quality video database
- 2010, VQEG HDTV Phase I Database
Cited by
VBench: Comprehensive Benchmark Suite for Video Generative Models
Huang, Z., He, Y., Yu, J., Zhang, F., Si, C., Jiang, Y., Zhang, Y., Wu, T., Jin, Q., Chanpaisit, N., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02060 · Cited by 407
“Meanwhile, the Video Quality Assessment (VQA) methods [63, 94, 108–114] are primarily designed for real videos, thereby neglecting the unique challenges posed by generative models, such as artifacts in synthesized videos.”
MethodSelf-citationFAST-VQA: Efficient End-to-End Video Quality Assessment with Fragment Sampling
Wu, H., Chen, C., Hou, J., Liao, L., Wang, A., Sun, W., Yan, Q., & Lin, W. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20068-7_31 · Cited by 244
Perceptual video quality assessment: a survey
Min, X., Duan, H., Sun, W., Zhu, Y., & Zhai, G. (2024) · Science China Information Sciences · doi:10.1007/s11432-024-4133-3 · Cited by 218
RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content
Tu, Z., Yu, X., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2021.3090333 · Cited by 215
“Among these, BRISQUE [8], GM-LOG [11], FRIQUEE [12], V-BLIINDS [9], and VIDEVAL [6] have leveraged different sets of natu-ral scene statistics (NSS)-based quality-aware features, using them to train shallow regressors to predict subjective quality scores.”
BackgroundMethodInfluentialSelf-citationWu, H., Zhang, E., Liao, L., Chen, C., Hou, J., Wang, A., Sun, W., Yan, Q., & Lin, W. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01843 · Cited by 215
“Recent Video Quality Assessment (VQA) studies have gathered enormous human quality opinions [1–5] on in-the-wild user-generated contents (UGC) and attempted to use machine algorithms [6–8] to learn and predict these opinions, known as the UGCVQA problem [9].”
BackgroundInfluential
Metadata
- Authors
- Tu, Z., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C.
- Affiliations
- The University of Texas at Austin (US)
- Google (United States) (US)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2021
- Volume
- 30
- Pages
- 4449-4464
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W3030701471
- Semantic Scholar
- a0d2b46a4ee9eca6f32df1c6f6bf7b1fbe6c0e0e
- Cited by
- 363
- References
- 81
- Citations by year
- 2026: 40 · 2025: 75 · 2024: 84 · 2023: 74 · 2022: 46 · 2021: 36
- FWCI
- 21.56
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Keywords
- blind video quality assessment, user-generated content, benchmark, feature selection, feature fusion, computational efficiency, perceptual video quality, in-the-wild videos, video streaming
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 (qwen3.8-omni-flash and 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.