The 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.
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
Open accessAbstract
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-citation
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
Items 101–200 of 320
Delving Deep into Engagement Prediction of Short Videos
Li, D., Li, W., Lu, B., Li, H., Ma, S., Krishnan, G., & Wang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72949-2_17 · Cited by 12
Full-Reference and No-Reference Quality Assessment for Video Frame Interpolation
Han, J., Min, X., Jia, J., Gao, Y., Liu, X., & Zhai, G. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3540104 · Cited by 11
“A. Experimental Settings 1) Datasets: Following the tradition [40], all three relevant datasets introduced in Section II-B are used separately for training and validation.”
FVQ: A Large-Scale Dataset and an LMM-based Method for Face Video Quality Assessment
Wu, S., Li, Y., Xu, Z., Gao, Y., Duan, H., Sun, W., & Zhai, G. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755332 · Cited by 16
Varga, D. (2022) · Sensors · doi:10.3390/s22249696 · Cited by 9
“[84] applied only 100 random splits, while the other papers used lower numbers of repetitions, i.”
MethodInfluentialDynamic Expert-Knowledge Ensemble for Generalizable Video Quality Assessment
Chen, P., Li, L., Li, H., Wu, J., Dong, W., & Shi, G. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3225552 · Cited by 11
“…model is trained and tested on the single domain, and seven top-performing metrics are included: V-BLIINDS [34], VIIDEO [35], TLVQM [36], VIDE-VAL [37], VSFA [10], RIRNet [11], PVQ [12] and LSCT-PHIQNet [50]; 2) multi-source unsupervised, which means the model is trained on multiple source…”
MethodMRET: Multi-resolution transformer for video quality assessment
Ke, J., Zhang, T., Wang, Y., Milanfar, P., & Yang, F. (2023) · Frontiers in Signal Processing · doi:10.3389/frsip.2023.1137006 · Cited by 10
“Conventional NR metrics (Saad et al., 2014; Mittal et al., 2015; Li et al., 2016; Sinno and Bovik, 2019; Dendi and Channappayya, 2020; Korhonen, 2019; Tu et al., 2021) utilize distortion-specific features and low-level features like natural scene statistics (NSS).”
BackgroundSelf-citationBH-VQA: Blind High Frame Rate Video Quality Assessment
Lu, W. H., Sun, W., Zhang, Z., Tu, D., Min, X., & Zhai, G. (2023) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme55011.2023.00426 · Cited by 12
Luminance 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
Subjective and Objective Quality Assessment of Rendered Human Avatar Videos in Virtual Reality
Chen, Y.-C., Saha, A., Chapiro, A., Häne, C., Bazin, J., Qiu, B., Zanetti, S., Katsavounidis, I. X., & Bovik, A. C. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3468881 · Cited by 11
“A selection of prominent generic NR IQA/VQA models, namely BRISQUE [69], CONTRIQUE, TLVQM [70], VIDEVAL [71], ChipQA [72], FAVER [73], VSFA [74], RAPIQUE [75], CONVIQT, GAMIVAL [76], and Re-IQA (quality only, content only, content + quality) [62], were tested.”
MethodSelf-citationUNQA: Unified No-Reference Quality Assessment for Audio, Image, Video, and Audio-Visual Content
Cao, Y., Min, X., Gao, Y., Sun, W., Ye, L., Lin, W., & Zhai, G. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3616155 · Cited by 14
“• Handcrafted feature-based VQA models: V-BLIINDS [62], VIDEVAL [63], and RAPIQUE [64].”
Towards versatile multimedia quality assessment for visual communications
Zhang, Z., Jia, Z., Li, C., Zhou, Y., Liu, X., Min, X., & Zhai, G. (2026) · Science China Information Sciences · doi:10.1007/s11432-025-4631-2 · Cited by 18
“…[92], NIQE [93], NIMA [94], DBCNN [95], HyperIQA [96], MUSIQ [97], CLIP-IQA+ [98], LIQE [99]; • VQA methods (8): TLVQM [100], VSFA [101], VIDEVAL [102], PVQ [88], BVQA [103], DisCoVQA [104], SimpleVQA [105], FAST-VQA [106]; • 3DQA methods (7): IT-PCQA [107], ResSCNN [108], PQA-Net [90], 3D-NSS…”
Increasing the Robustness of Image Quality Assessment Models Through Adversarial Training
Chistyakova, A., Antsiferova, A., Khrebtov, M., Lavrushkin, S., Arkhipenko, K. V., Vatolin, D. S., & Турдаков, Д. (2024) · Technologies · doi:10.3390/technologies12110220 · Cited by 11
Ntire 2025 Challenge on Short-Form Ugc Video Quality Assessment and Enhancement: Methods and Results
Li, X., Yuan, K., Li, B., Guan, F., Shao, Y., Yu, Z., Wang, X., Lu, Y., Luo, W., Yao, S., et al. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00106 · Cited by 9
“There are lots of studies that have been devoted to video/image quality assessment (VQA)[46, 59, 70, 73, 76, 80, 87, 92, 99, 106, 107] and image super-resolution[4, 31, 33, 41, 43, 50, 58, 83, 94] .”
Self-citationNo-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
The Short Video Popularity Prediction Using Internet of Things and Deep Learning
He, Z., & Li, D. (2024) · IEEE Access · doi:10.1109/access.2024.3383060 · Cited by 15
“By mapping the original input data into their high-level representations, the fusion of diverse modal information and the acquisition of cross-modal representations become more achievable [33], [34], [35].”
BackgroundAn Empirical Study for Efficient Video Quality Assessment
Sun, W., Fu, K., Cao, L., Zhu, D., Zhang, K., Zhu, Y., Zhang, Z., Hu, M., Min, X., & Zhai, G. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00129 · Cited by 11
“VIDEVAL [44] is a fusion-based BVQA model that selects 60 statistically effective features from existing efficient BI/VQA models to achieve a balance between prediction performance and computational cost for UGC videos.”
Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric
Zhang, Z., Sun, W., Li, X., Li, Y., Ge, Q., Jia, J., Zhang, Z., Ji, Z., Sun, F., Jui, S., et al. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754731 · Cited by 19
“Knowledge-driven BVQA methods leverage prior knowledge to extract quality features ( e.g., natural scenes statistics features) for quality regression, such as TLVQM [38], VIDEVAL [77], RAPIQUE [78], etc.”
Full-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 9
From Whole Video to Frames: Weakly-Supervised Domain Adaptive Continuous-Time QoE Evaluation
Li, L., Chen, P., Lin, W., Xu, M., & Shi, G. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3190711 · Cited by 8
Vishwakarma, A. K., & Bhurchandi, K. M. (2022) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103676 · Cited by 8
No-Reference Quality Assessment of Variable Frame-Rate Videos Using Temporal Bandpass Statistics
Zheng, Q., Tu, Z., Fan, Y., Zeng, X., & Bovik, A. C. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746997 · Cited by 11
Self-citationConvolutional 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 9
“Fortunately, many video quality models [29–34] have been proposed in recent years.”
BackgroundSelf-citationKVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception
Qu, Y., Yuan, K., Xie, Q., Sun, M. Y., Zhou, C., & Wang, J. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00206 · Cited by 10
“Due to the difficulty in obtaining reference videos in most user-generated content scenarios, we focus on the No-Reference (NR) VQA domain [19, 24, 47].”
Ying, Z., Pan, D., & Shi, P. A. (2023) · Sensors · doi:10.3390/s23031511 · Cited by 6
“The main models being compared have all been designed for video quality assessment in recent years, and include VSFA [38], TLVQM [39], VIDEVAL [40], GSTVQA [18], RAPIQUE [10], ChipQA [17], NOFU [6], HEKE [9] and”
MethodInfluentialIs AI-generated content better? A study based on Ant Forest Game content recommendation
Chen, Y., She, S., & Sun, Y. (2024) · Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence (DEAI) · doi:10.1145/3675417.3675543 · Cited by 6
Study of Subjective and Objective Quality Assessment of Night-Time Videos
Guan, X., Li, F., Huang, Z., & Liu, H. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3177518 · Cited by 7
Visual Mechanisms Inspired Efficient Transformers for Image and Video Quality Assessment
You, J., & Zhang, Z. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-28073-3_33 · Cited by 7
Blind video quality assessment based on Spatio-Temporal Feature Resolver
Bi, X.-D., He, X., Xiong, S., Zhao, Z., Chen, H., & Sheriff, R. E. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127249 · Cited by 6
Multi-Dimensional Feature Fusion Network for No-Reference Quality Assessment of In-the-Wild Videos
Jiang, J. C., Wang, X., Li, B., Tian, M., & Yao, H. (2021) · Sensors · doi:10.3390/s21165322 · Cited by 6
“Based on the study of different feature distributions for different datasets, UGCVQA [64] considered a selected fusion of BVQA models to reduce the inconsistency in subjective assessment among datasets.”
No-Reference Video Quality Assessment with Heterogeneous Knowledge Ensemble
Wu, J., Liu, Y., Li, L., Dong, W., & Shi, G. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475550 · Cited by 6
“The proposed method is compared with three FR-VQA methods (MS-SSIM [27], ST-RRED [23] and MOVIE [20]), three NR-VQA meth-ods (VBLIINDS [19], VIIDEO [14] and NSTSS [18]), and several UGC-VQA methods (VSFA [10], TL-VQM [9], and VIDEVAL [25]).”
BackgroundMethodVision-Language Model Guided Semi-supervised Learning for No-Reference Video Quality Assessment
Mitra, S., & Soundararajan, R. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890466 · Cited by 5
“While several algorithms based on hand-crafted features [1] and deep learning [2] have been designed, they all require a large number of human annotations to train these models.”
Semi-Supervised Learning of Perceptual Video Quality by Generating Consistent Pairwise Pseudo-Ranks
Mitra, S., Jogani, S., & Soundararajan, R. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3347090 · Cited by 5
“The line plots in each subfigure correspond to the SROCC performance of each VQA model trained for 30, 60, and 120 label cases and tested on a different database.”
MethodUltrahigh-definition video quality assessment: A new dataset and benchmark
Li, R., Wang, W., Hu, H., Chen, T., & Zhao, M. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127633 · Cited by 5
TQP: An Efficient Video Quality Assessment Framework for Adaptive Bitrate Video Streaming
Aslam, M. A., Xu, W. Z., Ahmed, N., Saleem, G., Shuangtong, Z., Xu, Y., & Hu, H. (2024) · IEEE Access · doi:10.1109/access.2024.3418375 · Cited by 5
No-reference video quality assessment based on human visual perception
Zhou, Z., Kong, G., Duan, X., & Long, H. (2024) · Journal of Electronic Imaging · doi:10.1117/1.jei.33.4.043029 · Cited by 5
“Our proposed method demonstrates an improvement of SROCC by 1.0% to 31.1% and PLCC by 2.8% to 30.0% compared to traditional methods; 12,13,24,26 compared to deep learning method, 1 our method improves SROCC by 2.8% to 12.9% and PLCC by 0.6% to 11.4%.”
InfluentialBeyond Correlation: Evaluating Multimedia Quality Models With the Constrained Concordance Index
Ragano, A., Martinez, H. B., & Hines, A. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3542991 · Cited by 11
“Incontrolledenvironments,wheredegradationlevelscanbe syntheticallygenerated,theMOSrangeadequatelyreflectsthe scopeofthedomainwithinwhichonewantstodevelopaqual-itymodel.”
A Review of Learning-Based Methods for Adaptive Video Streaming Over HTTP
Amer, H., Hassan, M. S., & Ismail, M. H. (2025) · IEEE Access · doi:10.1109/access.2025.3582850 · Cited by 6
“Similarly, the VIDEVAL [164] and RAPIQUE [165] models have recently been developed for NR-VQA of UGC.”
He, Q., Yang, C., Yang, F., & An, P. (2022) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103579 · Cited by 5
Rate-Distortion Optimization with Alternative References for UGC Video Compression
Xiong, X., Pavéz, E., Ortega, A., & Adsumilli, B. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096487 · Cited by 5
“We use NIQE and a no-reference quality metric for UGC video, VIDE [23] for quality evaluation.”
MethodSelf-citationSB-VQA: A Stack-Based Video Quality Assessment Framework for Video Enhancement
Huang, D.-J., Kao, Y.-T., Chuang, T.-H., Tsai, Y.-C., Lou, J.-K., & Guan, S.-H. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00163 · Cited by 7
Inverse-tone-mapped HDR video quality assessment: A new dataset and benchmark
Fan, L., Yang, A., Guo, C., Jiang, X., Gao, Y., & Min, X. (2023) · Displays · doi:10.1016/j.displa.2023.102510 · Cited by 5
Revisiting the robustness of spatio-temporal modeling in video quality assessment
Yan, J., Wu, L., Jiang, W., Liu, C., & Shen, F. (2023) · Displays · doi:10.1016/j.displa.2023.102585 · Cited by 5
A Database and Model for the Visual Quality Assessment of Super-Resolution Videos
Zhou, F., Wei, S., Lu, Z., & Qiu, G. (2024) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2024.3382949 · Cited by 10
“…demonstrate the effectiveness of the proposed SR VQA method, we compare it with some quality assessment methods on VSR-QAD: PSNR, SSIM [7], VIF [79], VMAF [80], SRIF [18], SpEED-QA [36], VIDEVAL [35], VSFA [9], GSTVQA [10], STI-VQA [81], DR-IQA [6], IGTS [15], DeepSRQ [16], DISQ [14], and STF [82].”
MethodSubjective Quality Assessment of Compressed Tone-Mapped High Dynamic Range Videos
Venkataramanan, A. K., & Bovik, A. C. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3463418 · Cited by 6
“As in [33] and [40], we used these low-level descriptors to illustrate the content diversity of the source videos in the LIVE-TM-HDR database.”
MethodSelf-citationBlind light field image quality assessment with tensor color domain and 3D shearlet transform
Xiang, J., Yu, M., Jiang, G., et al. (2023) · Signal Processing · doi:10.1016/j.sigpro.2023.109083 · Cited by 5
Liyanage, K. P. T. L. W., & Balalle, H. (2024) · Open Journal of Applied Sciences · doi:10.4236/ojapps.2024.149175 · Cited by 6
Detection of Air Pollution in Urban Areas Using Monitoring Images
Chu, Y., Chen, F., Fu, H. C., & Yu, H. (2023) · Atmosphere · doi:10.3390/atmos14050772 · Cited by 6
Value Assessment of UGC Short Videos through Element Mining and Data Analysis
Fang, J., Ni, Y., & Zhang, J. (2023) · Applied Sciences · doi:10.3390/app13169418 · Cited by 5
“Tu et al. [8] enhanced the performance of the reference-free VQA video value assessment model (BVQA) by incorporating a feature selection strategy, which demonstrated favorable results.”
MethodEfficient Computational Cost Saving in Video Processing for QoE Estimation
Llorente, Á., Pérez, J., Rodrigo, J. A., Jiménez, D., & Menéndez, J. M. (2024) · IEEE Access · doi:10.1109/access.2024.3373193 · Cited by 4
“VIDEVAL [88] focuses on spatial distortions selecting a combination of simple distortion-aware statistical video features, NSS statistics, and well-defined visual impairment features.”
BackgroundFull-Reference Video Quality Assessment for User Generated Content Transcoding
Qi, Z., Chen, F., Danier, D., Zhang, F., Xu, X., Liu, S., & Bull, D. (2024) · Picture Coding Symposium · doi:10.1109/pcs60826.2024.10566416 · Cited by 5
“Our proposed method was tested against 7 existing FR VQA methods (PSNR, SSIM, MS-SSIM [3], LPIPS [7], VMAF [6], C3DVQA [8] and RankDVQA [9]), and 6 NR quality metrics (NIQE [11], BRISQUE [13], VIIDEO [29], VBLIINDS [12], VIDEVAL [14] and SimpleVQA [15]).”
MethodADS-VQA: Adaptive sampling model for video quality assessment
Cheng, S., Li, X., Zeng, Z., & Yan, J. (2024) · Displays · doi:10.1016/j.displa.2024.102792 · Cited by 3
Liu, Z., Zeng, H., Chen, J., Ding, R., Shi, Y., & Hou, J. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3469180 · Cited by 4
“…SQMS [55], MDOGS [34], GFM [56]), VQA models specialized for SCVs (i.e., SGFTM [21], HSFM [41], SCVQA [17]), NR-VQA models specialized for in-the-wild videos or User-Generated Content (UGC) videos (i.e., TLVQM [25], VSFA [8], GSTVQA [28], VIDEVAL [26], SimpleVQA [9], FastVQA [13], SAMA [31]).”
Study on no-reference video quality assessment method incorporating dual deep learning networks
Li, J., & Li, X. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13383-0 · Cited by 5
“[44] obtained 763dimensional features from BRISQUE [32], GM-LOG [48], HIGRADE [22], FRIQUEE [15] and TLVQM and then predicted the quality of the video by support vector regression.”
MethodMotion measurement and quality variation driven video quality assessment
Hu, Z., & Liu, L. (2022) · Displays · doi:10.1016/j.displa.2022.102289 · Cited by 4
Blind Video Quality Assessment via Space-Time Slice Statistics
Zheng, Q., Tu, Z., Hao, Z., Zeng, X., Bovik, A. C., & Fan, Y. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897565 · Cited by 4
“General-purpose BVQA models have shown promising performance, based on the measurements of distortion-induced deviations of bandpass-filtered images/videos inspired by natural scene statistics (NSS) [6, 15, 16].”
BackgroundMethodInfluentialSelf-citationA fine-grained intrusion protection system for inter-edge trust transfer
Yang, B., Wu, D. O., Wang, R., Yang, Z., & Yang, Y. (2022) · Digital Communications and Networks · doi:10.1016/j.dcan.2022.11.007 · Cited by 4
Integrates Spatiotemporal Visual Stimuli for Video Quality Assessment
Guo, W., Zhang, K., & Ke, X. (2023) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2023.3312932 · Cited by 5
“VIDEVAL [4] integrated many high-performance and efficient manual methods and designed feature selec-tors to reduce redundancy, thus improving generalisation performance.”
BackgroundMethodShort-form UGC Video Quality Assessment Based on Multi-Level Video Fusion with Rank-Aware
Xu, H., Yang, M., Zhou, J., & Li, J. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00633 · Cited by 4
“TLVQM [10] and VIDE-VAL [32] merge an extensive array of spatial-temporal features with traditional quality metrics in order to translate them into a numerical representation of video quality.”
BackgroundComputer Vision in the Infrared Spectrum: Challenges and Approaches
Teutsch, M., Sappa, A. D., & Hammoud, R. I. (2021) · Synthesis lectures on computer vision · doi:10.2200/s01127ed1v01y202109cov019 · Cited by 10
Optimized Quality Feature Learning for Video Quality Assessment
Kwong, N.-W., Chan, Y., Tsang, S., & Lun, D. P.-K. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095975 · Cited by 2
“Seven NR-VQA methods, TLVQM [8], VSFA [9], CNN-TLVQM [10], HEKE [31], RAPIQUE [32], VIDEVAL [33], and MDTVSFA [34] were included to evaluate the performance of our proposed model.”
MethodA multi-scale no-reference video quality assessment method based on transformer
Cui, Y., Yu, Z., Feng, Y., Wang, H., & Li, J. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01403-y · Cited by 3
“In this section, classic video quality assessment meth-ods were selected for comparison, including VSFA [13], BRISQUE [16], NIQE [17], V-BLIINDS [18], VIIDEO [19], TLVQM [20], VIDEVAL [21], RAPIQUE [22], MDTVSFA [23], HEKE [24] and Shen et al. [25].”
An Ensemble Approach to Short-form Video Quality Assessment Using Multimodal LLM
Wen, W., Wang, Y., Birkbeck, N., & Adsumilli, B. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888524 · Cited by 5
“BVQA models encompass both knowledge-based models [1]–[4] and learning-based models [5]–[13], showcasing substantial progress.”
Self-citationVQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results
Li, D., Ma, S., Hua, H., Li, W., Wang, J., Zhou, C. W., Guan, F., Li, X., Yu, Z., Lu, Y., et al. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00359 · Cited by 6
“56], reduced-reference [32, 38], and no-reference approaches [16, 40, 43, 54].”
A No Reference Deep Learning Based Model for Quality Assessment of UGC Videos
Lamichhane, K., Mazumdar, P., Battisti, F., & Carli, M. (2021) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew53276.2021.9456011 · Cited by 4
Specialised Video Quality Model For Enhanced User Generated Content (UGC) With Special Effects
Perrin, A.-F., Xie, Y., Zhang, T., Liao, Y., Li, J., & Callet, P. L. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746539 · Cited by 3
Revisiting the Efficiency of UGC Video Quality Assessment
Wang, Y., Yim, J. G., Birkbeck, N., Ke, J., Talebi, H., Chen, X., Yang, F., & Adsumilli, B. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897401 · Cited by 3
“Later, machine learning models (e.g., SVM) were introduced to aggregate multiple features [2], and recent works such as TLVQM [14], VIDEVAL [15], and RAPIQUE [16] use up to hundreds of manually designed features.”
MethodSelf-citationOn the Importance of Spatio-Temporal Learning for Video Quality Assessment
Fontanel, D., Higham, D., & Vallade, B. Q. A. (2023) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw58289.2023.00053 · Cited by 3
“With the constant growth of services that offer video content as a form of entertainment for customers, video quality assessment (VQA) has attracted more and more interest recently [24, 22, 9, 26, 21, 5, 10].”
BackgroundZhang, Y., Yang, M., Huang, Z., He, L., & Wu, Z. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04624-2 · Cited by 3
“Aiming at UGC videos, TLVQM [17] and VIDEVAL [34] have superior accuracy with well-chosen and carefully designed quality-aware features.”
BackgroundMethodInfluentialNRspttemVQA: Real-Time Video Quality Assessment Based on the User’s Visual Perception
Mozhaeva, A., Mazin, V., Cree, M. J., & Streeter, L. V. (2023) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz61134.2023.10343863 · Cited by 3
“We compared the proposed NR VQA with the world’s most widely used full reference metrics SSIM, PSNR, full reference metrics containing models of the human visual system FovVideoVDP [4] and PSNR-M+ [6], and popular shallow NR video modes BRISQUE [40], VIDEVAL [41].”
MethodFeature Maps Correlation-based Video Quality Assessment
Bakhtiari, A. H., & Mansouri, A. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-023-18068-w · Cited by 3
“However, as user-generated material with various types of distortions has increased, new methods for assessing the quality of such videos have emerged [3, 4].”
InfluentialExploiting User-Generated Content in Product Launch Videos to Compute a Launch Score
Das, S. D., Bala, P. K., & Das, S. K. (2024) · IEEE Access · doi:10.1109/access.2024.3381541 · Cited by 3
Blind Video Quality Assessment at the Edge
Mei, Z., Wang, Y.-C., & Kuo, C. ‐. J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3521704 · Cited by 5
“We compare the PLCC and SROCC performance of GreenBVQA with that of the other eleven benchmarking methods in Table VI. GreenBVQA out-performs all three conventional BIQA methods (i.e., NIQE, BRISQUE, and CORNIA) and all three conventional BVQA methods (i.e., V-BLIINDS, TLVQM, and VIDEVAL) by a substantial margin in al…”
Self-citationA Projection-based no-reference point cloud quality assessment metric based on perceptual features
Goswami, A., Lambat, N., & Mazumdar, P. (2025) · Displays · doi:10.1016/j.displa.2025.103098 · Cited by 4
Perceptual Quality Assessment of 360° Images Based on Generative Scanpath Representation
Sui, X., Zhu, H., Liu, X., Fang, Y., Wang, S., & Wang, Z. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3583181 · Cited by 13
“A. Objective Quality Assessment of 2D Images and Videos PSNR and SSIM [25] are the two most popular full-reference measures for image quality assessment, and they also trigger the development of quality models, including knowledge-driven and data-driven methods [26], [27].”
Memory-VQA: Video quality assessment of UGC based on human memory system
Sun, M., Kong, G., Duan, X., & Long, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130852 · Cited by 2
A Progressive Architecture for Learned Fractional Downsampling
Chen, L., Bampis, C. G., Li, Z., Solé, J., & Bovik, A. C. (2021) · Picture Coding Symposium · doi:10.1109/pcs50896.2021.9477407 · Cited by 3
Self-citationFeature‐based no‐reference video quality assessment using Extra Trees
Shahreza, H. O., Amini, A., & Behroozi, H. (2022) · IET Image Processing · doi:10.1049/ipr2.12428 · Cited by 3
Telepresence Video Quality Assessment
Ying, Z., Ghadiyaram, D., & Bovik, A. C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19836-6_19 · Cited by 4
Self-citationMVAD: A Multiple Visual Artifact Detector for Video Streaming
Chen, F., Danier, D., Zhang, F., Mackin, A., Collins, A., & Bull, D. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00311 · Cited by 3
“…assessment is a well-established research area, with numerous classic [45, 47, 53, 30, 28, 29, 35] and learning-based approaches [23, 19, 21, 42, 11] developed over the past two decades, these methods can only provide a quantitative prediction of perceptual quality, rather than detect and…”
BackgroundPeng, T., Feng, C., Danier, D., Zhang, F., Vallade, B. Q. A., Mackin, A., & Bull, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91838-4_7 · Cited by 4
“Conventional blind VQA methods [43,45,55] are predominantly based on various features extracted in the spatio-temporal or/and frequency domains.”
BackgroundMethodHu, B., Wang, W., Li, L., He, L., Lu, W. B., & Gao, X. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3585993 · Cited by 3
“Tu et al. [33] proposed an e ffi cient and high-performance UGC video quality evaluator, VIDEVAL, providing a reliable benchmark for the UGC-VQA.”
Frame Differences Matter in Quality Assessment of Compressed Videos
Wang, X., Katsenou, A., & Bull, D. (2025) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/dsp65409.2025.11075040 · Cited by 2
“Numerous NR-VQA models have been developed based on Natural Scene Statistics (NSS) and hand-crafted features, such as BRISQUE [4], BLIINDS [5], V-CORNIA [6], TLVQM [7] and VIDEVAL [8].”
Zhang, H., Geng, X., Zhang, Y., Du, Y., & Li, D. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103948 · Cited by 2
Pu, Y., Li, K., Huang, Z., Zhong, Z., & Yang, K. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754824 · Cited by 4
Distortion-Sensitive Masked Autoencoder for Omnidirectional Video Quality Assessment
Hu, Z., Liu, L., Gu, K., Li, L., & Bovik, A. C. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3651128 · Cited by 2
Self-citationFew-Shot Image Quality Assessment via Adaptation of Vision-Language Models
Li, X., Huang, Z. P., Zhang, Y., Shen, Y., Li, K., Zheng, X., Cao, L., & Ji, R. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00972 · Cited by 6
“These models use various methods to assess image quality.”
A Temporal Statistics Model For UGC Video Quality Prediction
Tu, Z., Chen, C.-J., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506669 · Cited by 2
“As a highly experimental temporal-only model, VIIDEO includes no spatial features, which has been shown essential for UGC video quality [2], hence does not perform well on natu-ral user-generated video datasets [29–31].”
BackgroundMethodInfluentialSelf-citationEfficient Transformer with Locally Shared Attention for Video Quality Assessment
You, J., & Lin, Y. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9898025 · Cited by 5
“Several other state-of-the-art VQA models have been included in our experiments as benchmarks, including VBLIINDS [3], 3DCNN [13], VSFA [15], VIDEAL [17], ST-3DDCT [18], and TLVQM [31].”
BackgroundMethodInfluentialA Database for Multi-Modal Short Video Quality Assessment
Zhang, Y., Wang, C., Zhang, S., & Cao, X. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10097274 · Cited by 3
Fusion-based Representation Learning Model for Multimode User-generated Social Network Content
Martin, J., Oak, R., Soni, M., et al. (2023) · Journal of Data and Information Quality · doi:10.1145/3603712 · Cited by 2
“Representation learning has achieved many research results in text and image classification [4-8].”
BackgroundUsing Spatial‐Temporal Attention for Video Quality Evaluation
Chi, B., Su, R., & Chen, X. (2024) · International Journal of Intelligent Systems · doi:10.1155/2024/5514627 · Cited by 2
Tan, X., Zhang, J., Quan, Y., Li, J., Wu, Y., & Bian, Z. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680907 · Cited by 3
Blind Video Quality Prediction by Uncovering Human Video Perceptual Representation
Liao, L., Xu, K., Wu, H., Chen, C., Sun, W., Yan, Q., Kuo, C. ‐. J., & Lin, W. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3445738 · Cited by 4
“VIDEVAL [13] is a bag-of-features based VQA model that leverages a feature ensemble and selection procedure on top of existing efficient blind VQA models.”
BackgroundMethodInfluentialQPT-V2: Masked Image Modeling Advances Visual Scoring
Xie, Q., Yuan, K., Qu, Y., Wu, M., Sun, M., Zhou, C., & Zhu, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680721 · Cited by 3
“Facilitated by the advancements of deep neural networks [22, 36, 76], learning-based methods [24, 38, 67] have surpassed traditional methods [52, 73, 87] based on handcrafted features on multiple VS benchmarks [7, 14, 81].”
Mo, L., Yin, H., Wang, H., Huang, X., Lin, J., Xie, Y., Liu, Y., Sheng, N., & Tang, X. (2024) · Signal Processing · doi:10.1016/j.sigpro.2024.109819 · Cited by 4
Subjective and Objective Analysis of Indian Social Media Video Quality
Mishra, S., Jha, M., & Bovik, A. C. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3512376 · Cited by 2
“We selected six well-known general-purpose NR-VQA models to test: NIQE [19], BRISQUE [20], VIDE-VAL [21], RAPIQUE [22], and CONTRIQUE [31].”
MethodSelf-citationA Robust Quality Evaluator for Panoramic Videos
Wang, Y., Feng, J., Zhou, Y., Tang, L., Chen, R., Sun, Y., & Ding, J.-C. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888289 · Cited by 2
Self-citationCLIP-Fusion: A Spatio-Temporal Quality Metric for Frame Interpolation
Çökmez, G. M., Zhang, Y., Schroers, C., & Aydın, T. O. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00724 · Cited by 2
“We compare the NR version of our model with other NR models tested in [6], including BRISQUE [32], ChipQA [7], VIDEVAL [35], deep-IQA NR [2], NIQE [28], VIIDEO [27], FastVQA [40], VBLIINDS [31], TLVQM [15], and FAVER [51].”
Who Is a Better Imitator: Subjective and Objective Quality Assessment of Animated Humans
Zhou, Y., Zhang, Z., Jia, J., Jiang, Y., Liu, X., Min, X., & Zhai, G. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3572000 · Cited by 2
Rozo-Torres, A., Latorre-Rojas, C. J., & Sarmiento, W. J. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-91328-0_20 · Cited by 2
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.