UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
Open accessThe DOI matches its Crossref record; 92 of the 94 references it cites were found in a registry or an index, and 2 are not checked yet; 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.
Verified 2026-11-20 · 2 references not checked yet
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: 1
- [19] L. V. D. Maaten and G. Hinton, 'Visualizing data using t-SNE,' J. Mach. Learn. Research , vol. 9, no. Nov, pp. 2579-2605, 2008. -
Cited by
Items 201–300 of 320
Secure Video Quality Assessment Resisting Adversarial Attacks
Zhang, A., Wang, Y., Ran, Y., Tang, W., Guan, Q., & Yang, C. (2025) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2025.3575339 · Cited by 7
“This paper first attempts to investigate general adversarial defense principles, aiming to endow existing VQA models with security.”
Self-citationRGC-VQA: An Exploration Database for Robotic-Generated Video Quality Assessment
Jin, J., Ying, J., Duan, H., Liu, Y., Wu, S., Li, Y., Zheng, Y., Min, X., & Zhai, G. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758304 · Cited by 7
Engagement Prediction of Short Videos with Large Multimodal Models
Sun, W., Cao, L., Cao, Y., Zhang, W., Wen, W., Zhang, K., Chen, Z., Lu, F., Min, X., & Zhai, G. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00360 · Cited by 10
“Specifically, handcrafted feature-based VQA methods [9, 14, 28, 31, 42, 43] primarily rely on manually designed features that capture fundamental perceptual cues such as brightness, contrast, edge sharpness, and motion artifacts.”
Guzman, K. J. D., & Robielos, R. A. C. (2022) · HighTech and Innovation Journal · doi:10.28991/hij-2022-03-01-07 · Cited by 2
“An appealing study on user generated content illustrated the result of difference video popularity and length between user generated content and non-user generated content [14-16].”
BackgroundLearning a Blind Quality Evaluator for UGC Videos in Perceptually Relevant Domains
Li, B., Zhang, W., Tian, M., Jiang, J. C., Zhai, G., & Wang, X. (2022) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme52920.2022.9859999 · Cited by 2
“The compared BVQA methods can be roughly classified into two groups: 1), four models with hand-crafted features, V-BLIINDS [2], TLVQM [3], VIDEVAL [4], and RAPIQUE [7]; and 2), three deep models involving VSFA [5], MDTVSFA [6], and PVQ [8].”
BackgroundMethodWhen is the Cleaning of Subjective Data Relevant to Train UGC Video Quality Metrics?
Perrin, A.-F., Dormeval, C., Wang, Y., Birkbeck, N., Adsumilli, B., & Callet, P. L. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897997 · Cited by 3
“VIDEVAL selects the best features from state-of-the-art metrics through random forest and fusion them with a Support Vector Regression (SVR).”
BackgroundMethodInfluentialSelf-citationDCVQE: A Hierarchical Transformer for Video Quality Assessment
Li, Z., & Yang, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26316-3_24 · Cited by 4
Blind consumer video quality assessment with spatial-temporal perception and fusion
Niu, Y., Zheng, Y., Wang, Z., Zhong, M., & Zhao, T. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16242-8 · Cited by 2
Quality assessment of enhanced videos guided by aesthetics and technical quality attributes
Agarla, M., Celona, L., Rota, C., & Schettini, R. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00156 · Cited by 2
“Second, the quality-related attribute encoder is trained using images containing various Method SROCC PLCC MainScore VIDEVAL [24] 0.5005 0.4724 0.4865 RAPIQUE [25] 0.5434 0.5393 0.5414 TLVQM [9] 0.5474 0.5509 0.5492 V-BLIINDS [19] 0.5652 0.5503 0.5578 VSFA [12] 0.5871 0.5424 0.5648 BVQA [10] 0.6995 0.6674 0.6835 FAST-…”
MethodInfluentialVisual Realism Assessment for Face-Swap Videos
Sun, X., Dong, B., Wang, C., Peng, B., & Dong, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46305-1_34 · Cited by 6
An End-to-End Fast No-Reference Video Quality Predictor with Spatiotemporal Feature Fusion
Vishwakarma, A. K., & Bhurchandi, K. M. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-31417-9_48 · Cited by 1
STAN: Spatio-Temporal Alignment Network for No-Reference Video Quality Assessment
Yang, Z., Dang, Y., Xiang, J., & Chen, P. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44213-1_14 · Cited by 3
One-class graph moderating attention neural network in quality assessment of creative ideas
Yang, Y. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09256-8 · Cited by 1
“Traditional research built the assessment system and identification framework through qualitative analysis [4–6, 35– 39 To overcome the ineffective results, some researchers have constructed the machine learning model based on the quantitative analysis of factors [18–20, 40, 41], such as random…”
Wu, J.-T., Ichihara, H., Inoue, T., et al. (2024) · IEEE International Test Conference in Asia (ITC-Asia) · doi:10.1109/itc-asia62534.2024.10661349 · Cited by 1
MT-VQA: A Multi-task Approach for Quality Assessment of Short-form Videos
Wen, S., Qiao, M., Jiang, L. W., Xu, M., Deng, X., & Li, S. (2024) · Workshop on Quality of Experience in Visual Multimedia Applications (QoEVMA) · doi:10.1145/3689093.3689181 · Cited by 4
Quantizing Neural Networks with Knowledge Distillation for Efficient Video Quality Assessment
Yu, J. Y., & Li, Y. (2024) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip63160.2024.10849844 · Cited by 1
“We consider the following baseline methods for comparisons: (1) Classical Methods: including TLVQM [4] and VIDEVAL [30].”
Ma, G., Xu, H., Chen, B., et al. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07666-0 · Cited by 1
“The PEAQ algorithm computes a set of perceptual features [40], including the excitation pattern, the modulation difference, and the noise-to-mask ratio.”
Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos
Zheng, Q., Chen, L., He, C., Birkbeck, N., Wang, Y., Adsumilli, B., Bovik, A. C., Fan, Y., & Tu, Z. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3592543 · Cited by 1
“Five NR VQA models were also included: VIDEVAL [82], TLVQM [83], FAVER [73], RAPIQUE [72], and deep learning-based models: VSFA [34], FAST-VQA [84], FasterVQA [85], DOVER [86], SAMA [87], and ModularBVQA [88].”
Self-citationBlind Real-Time Interaction Quality of Experience Assessment for Low Latency Services
Zhang, D., Zhang, C., & Luo, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9812-7_2 · Cited by 1
DIVA-VQA: Detecting Inter-Frame Variations in UGC Video Quality
Wang, X., Katsenou, A., & Bull, D. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084568 · Cited by 4
“Although classical NR models [10, 11, 12, 6] perform well on small-scale datasets, they remain inadequate when addressing the complex spatio-temporal distortions associated with UGC video content.”
LMVQ: Label-Free Metric-Learning for General AI-Generated Video Quality Assessment
Zhang, Z., Li, X., Sun, W., Zhang, Z., Liu, X., Min, X., & Zhai, G. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3618655 · Cited by 4
MSTVQA: A multi-path dynamic perception method for video quality assessment
Qi, J., Wang, Y., Gao, J., Wu, Y., & Liu, P. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105891 · Cited by 1
Self-citationUsability Assessment Framework for Crowdsensing Data and the Implicit Spatiotemporal Information
Chen, Y., Zhang, H., Zhang, J., Shen, J., & Li, Y. (2026) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi15010029 · Cited by 2
Convolutions Need Registers Too: HVS-Inspired Dynamic Attention for Video Quality Assessment
Mithila, M. M. R., & Farias, M. C. Q. (2026) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/3793853.3795745 · Cited by 2
“We evaluated DAGR-VQA on four standard no-reference VQA datasets: LSVQ [51], KonVid-1k [17], LIVE-VQC [33], and YouTube-UGC [37].”
Subjective and Objective QoE Assessment for Real-Time Streaming Interactive Digital Human
Zhou, Y., Wan, J., Wen, F., Zhang, Z., Liu, X., Zhou, Y., Cao, J., Wang, Y., Min, X., & Zhai, G. (2026) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3820052 · Cited by 1
Self-citationBlind visual quality assessment for super-resolution images: database and model
Zheng, R., Jiang, X., Zhang, J., & Yu, H. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17026-w · Cited by 1
STVP: A Spatiotemporal Visual Perception Method for User-generated Content Video Quality Assessment
Ai, D., Lu, M., Wang, J., & Liu, Y. (2023) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip59821.2023.10402648 · Cited by 3
“However, to account for the characteristics of the human visual system (HVS) and the temporal nature of video, some researchers have incorporated temporal features to enhance the model’s efficacy [9], [14], [22].”
BackgroundMethodSpatiotemporal feature learning for no-reference gaming content video quality assessment
Kwong, N.-W., Chan, Y., Tsang, S., Huang, Z., & Lam, K. (2024) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2024.104118 · Cited by 1
A Critical Review on Quality of Experience for Videos and User Engagement on Social Media Platforms
Choon, K. M., & Lim, T. M. (2024) · International Conference on Digital Transformation and Applications (ICDXA) · doi:10.1109/icdxa61007.2024.10470509 · Cited by 2
“A lot of research use video quality assessment (VQA) methods to automatically measure perceptual video quality in close agreement with the human visual judgment [22], [23], [24].”
BackgroundFowdur, T. P., & Babooram, L. (2024) · Apress eBooks · doi:10.1007/979-8-8688-0354-3_3 · Cited by 1
Learned fractional downsampling network for adaptive video streaming
Chen, L., Bampis, C. G., Li, Z., Solé, J., Chen, C., & Bovik, A. C. (2024) · Signal Processing Image Communication · doi:10.1016/j.image.2024.117172 · Cited by 4
Self-citationSuson, R., Atibing, N. M., Evangelista, S. S., Wenceslao, C., Maturan, F., Villarosa, R., & Ocampo, L. A. (2024) · Applied Artificial Intelligence · doi:10.1080/08839514.2024.2389501 · Cited by 5
“On the other hand, the combination of cost-effective and high-performance mobile devices (Tu et al. 2021) and substantial improvements in video streaming technologies (Li et al. 2020) has enabled the majority of consumers to create, share, and view user-generated pictures and videos in real-time,…”
SR4KVQA: Video quality assessment database and metric for 4K super-resolution
Zheng, R., & Jiang, X. (2024) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2024.104290 · Cited by 2
Priorformer: A UGC-VQA Method With Content and Distortion Priors
Pei, Y., Huang, S., Lu, Y., Li, X., & Chen, Z. (2024) · Proceedings - International Conference on Image Processing · doi:10.1109/icip51287.2024.10647869 · Cited by 4
ADCMT: An Augmentation-Free Dynamic Contrastive Multi-Task Transformer for UGC-VQA
Li, H., Zhang, K., Li, J., Gao, X., & Shi, G. (2025) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2025.3565888 · Cited by 1
“…NR-VQA methods (whose source codes are released by the authors) for comparison: BRISQUE [9], CORINA [81], BMPRI [27], RichIQA [28], V-BLIINDS [29], STEM [82], VIQE [83], VSFA [12], TLVQM [84], VIDEVAL [49], PVQ [8], VSFA+CSPT [42], SimpleVQA [37], RAPIQUE [85], and MinimalisticVQA [38].”
Kwong, N.-W., Chan, Y., Tsang, S., Huang, Z., & Lam, K. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3599071 · Cited by 2
A Real Haze Video Database for Haze Level Evaluation
Chu, Y., Luo, G., & Chen, F. (2021) · International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex51781.2021.9465461 · Cited by 5
Quality Assessment of In-the-Wild Videos via Multi-Scale Spatio-Temporal Feature Extraction
Liu, S., Li, X., & Zhang, X. (2022) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/iwecai55315.2022.00022
Super Resolution Image Visual Quality Assessment Based on Feature Optimization
Shu, L., Huang, Z., Yan, J., & Fei, F. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/1263348 · Cited by 1
“Besides, support vector machine (SVR) [23] is applied to learn a given number of features to build a model and predict the quality of SR images, and the PLCC between the predicted score and human subjective score is calculated.”
MethodInfluentialBlind Video Quality Assessment Using Fusion of Novel Structural Features and Deep Features
Vishwakarma, A. K., & Bhurchandi, K. M. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-11349-9_19
AI-empowered promotional video generation
Liu, C. (2022) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/161247 · Cited by 3
Quality assessment for super resolution image via feature optimization
Shu, L., Huang, Z., Yan, J., Wang, R., & Fan, J. (2022) · International Conference on Computer Engineering and Artificial Intelligence (ICCEAI) · doi:10.1109/icceai55464.2022.00067
A Hybrid Approach to Blind Video Quality Prediction of User Generated Content
Erabadda, B., Kulupana, G., Mallikarachchi, T., Wang, W., & Fernando, A. (2022) · Picture Coding Symposium · doi:10.1109/pcs56426.2022.10018033
“In addition, a subset of features from the SOTA NSS-based no-reference UGC metric VIDEVAL [9] is employed.”
MethodInfluentialVideo Quality Assessment based on Deep Neural Network
Shi, Z. (2023) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2023.08.005
Yang, Y., Jiang, B., & Wu, K. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10221996
Zhao, S., Yin, H., Wang, H., & Zhou, Y. (2023) · DCC · doi:10.1109/dcc55655.2023.00008
Mapping of Temporal Space Slicing for Video Quality Metrics Assessment
Bagade, S., Kumar, B. A., & Koteswara Rao, L. (2024) · International Journal of Electrical and Electronics Engineering · doi:10.14445/23488379/ijeee-v11i1p101
Enhancing video quality assessment through brightness information
Yuan, J., Peng, Y., & Zhang, A. (2024) · International Conference on Computer Vision and Data Mining (ICCVDM) · doi:10.1117/12.3021606
“In the context of the internet, where reference videos are often unavailable for most videos, NRVQA has emerged as a prominent and relevant research area [6, 7].”
BackgroundA Literature Survey on Completely Blind Image Quality Evaluator Feature-Enriched
Gavaeikar, D., & Singhai, D. (2023) · International Journal of Scientific Research in Science and Technology · doi:10.32628/ijsrst52310686
A Literature Survey on Completely Blind Image Quality Evaluator Feature-Enriched
Gavaeikar, D., & Singhai, D. (2024) · International Journal of Scientific Research in Science and Technology · doi:10.32628/ijsrst52310626
Sungman, H. (2024) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.1109/iceic61013.2024.10457245
Quality Modeling Under A Relaxed Natural Scene Statistics Model
Venkataramanan, A. K., & Bovik, A. C. (2024) · IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) · doi:10.1109/ssiai59505.2024.10508705 · Cited by 1
“A comprehensive evaluation of NR IQA models on UGC can be found in [13].”
BackgroundSelf-citationAMMAR, S., Kchaou, A., & Hamed, B. B. (2024) · Research Square · doi:10.21203/rs.3.rs-4372745/v1
Conformer Based No-Reference Quality Assessment for UGC Video
Yang, Z., Zhang, Y., & Si, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5597-4_39
Long Term UGC Video Quality Evaluation Based on Transformer
Lang, Z., & Zhang, L. (2024) · International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE) · doi:10.1145/3672758.3672836
Semantic-Aware and Quality-Aware Interaction Network for Blind Video Quality Assessment
Xiang, J., Dang, Y., Chen, P., Liang, R., Huan, R., & Gao, N. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680598 · Cited by 1
“Classic BVQA methods [6, 19, 25, 32, 35, 40] are designed to use hand-crafted features for describing visual quality degradation.”
SCAMS: Semantic Category-Aware Multi-scale Network for Video Quality Assessment
Ren, L., Zhang, K., Fan, D., & Shi, G. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8792-0_26 · Cited by 1
Chen, X., Ramasamy, S. S., She, B., & Udomwong, P. (2024) · Society Document Communication · doi:10.69587/sdc/2.2024.80
A Novel Patch Selection Approach for Quality Assessment on Short-Form Videos
Wen, S., Jiang, L. W., Qiao, M., Xu, M., Deng, X., Li, S., & Duan, Y. (2024) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp62071.2024.10826890
“In traditional VQA approaches [2]–[5], researchers extract handcrafted video features such as motion, jerkiness, blockiness, to assess video quality.”
Ultra-high definition video quality assessment method based on deep learning
Li, W., He, C., Zhou, M., Zhang, H., & Liu, W. (2024) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc63484.2024.00095
Enhancing Video Quality Assessment through Semantic Guidance
Wang, F., & Li, Z. (2024) · International Symposium on Artificial Intelligence and Intelligent Manufacturing (AIIM) · doi:10.1109/aiim64537.2024.10934500
“Traditional video quality assessment (VQA) models [2][3][4][5] rely on hand-crafted features for evaluating video quality, proving effective with laboratory-synthesized data.”
Multi-Branch Collaborative Learning Network for Video Quality Assessment in Industrial Video Search
Tang, H., Zhang, Z., Li, Z., Zhang, Z., Wu, X., Gao, L. P., Cheng, S., & Yin, D. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709408 · Cited by 2
“Numerous studies have leveraged hand-crafted features to capture quality perception features in videos [17, 28, 35, 41].”
An End-to-End Full-Reference and No-Reference Quality Assessment Model for 360$$^\circ $$ VR Videos
Pei, D., Jia, Z., Sun, W., Duan, H., & Min, X. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4279-3_22
AdaVQA: a semantic and quality-aware video quality assessment method
Zhang, A., & Wang, Y. (2025) · International Conference on Electronic Information Engineering and Data Processing (EIEDP) · doi:10.1117/12.3066937 · Cited by 2
Self-citationDC-HCVQA: a dark channel enhanced human cognitive system based video quality assessment
Sun, M., Kong, G., Duan, X., & Long, H. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04151-2
Vocal Course Quality Evaluation Model Using Hybrid Neural Networks and Meta-Learning Optimization
Lu, L., & Xu, M. (2025) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126625503694
Compression-RQ-VQA: Leveraging Rich Quality-Aware Features for Compressed Video Quality Assessment
Jia, Z., Qian, J., Sun, W., Zhang, Z., Cao, Y., Sun, Y., Zhu, Y., Zhai, G., & Min, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91856-8_5 · Cited by 1
SR-VQA: Super-Resolution Video Quality Assessment Model
Cao, Y., Sun, W., Zhang, W., Sun, Y., Jia, Z., Zhu, Y., Min, X., & Zhai, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91856-8_9 · Cited by 1
Role of Visual Saliency in Video Quality Assessments
Eesha-tir-Razia, S., Abbas, Q., Nizami, I. F., Raja, A. A., Aldajani, M. B., Wahab, M., Akram, T., & Ahmad, S. A. (2025) · IEEE Access · doi:10.1109/access.2025.3578043 · Cited by 1
“No-Reference Video Quality Assessment (NR-VQA), evaluates video quality without requiring a reference, making it the most suitable approach for real-world scenarios such as live streaming and user-generated content [6].”
Understanding, detecting, and removing perceptual banding artifacts in compressed videos
Tu, Z., Chen, C.-J., Lin, J., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2025) · Signal Processing Image Communication · doi:10.1016/j.image.2025.117372 · Cited by 1
Self-citationLPerceptual Quality Assessment of AI Generated Content Videos: a Dataset and Benchmark
Zhang, Z., Sun, W., Li, X., Li, Y., Jia, J., Min, X., Zhang, Z., Li, C., Ji, Z., Sun, F., et al. (2025) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas56072.2025.11043899 · Cited by 2
“For temporal quality, we test two handcrafted-based VQA models, i.e. TLVQA [18] and RAPIQUE [19], and six deep learning-based VQA models, i.e. VSFA [20], Sim-pleVQA [21], FastVQA [22], DOVER [23], VIDEAL [24] and PatchVQ [25].”
Energy Efficiency of Video Quality Assessment Metrics
Moan, S. L., Nguyen, H. T., & Amirshahi, S. A. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084706
Discerning MOS of Video Conferencing via Deep Packet Inspection and Video Context Clues
Qian, C., Huang, Y., Shi, T., Li, J., Xu, Q., Wu, K., Wang, J., & Liu, B. (2025) · International Workshop on Quality of Service · doi:10.1109/iwqos65803.2025.11143511
“Many recent works adopted the MOS metric to capture the QoE for multimedia communication [1], [13]–[15].”
Quality Assessment for Talking Head Videos via Multi-Modal Feature Representation
Su, M., Wang, Y., Chen, T., Li, C., Zhao, S., Wen, J., Lin, C., Liu, S., Chu, N., & Zhou, Y. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00130 · Cited by 2
“Among them, VMAF [36] is an FR VQA method, while VIIDEO [33], RAPIQUE [7], TLVQM [37], VIDEVAL [38], SimpVQA [6], and VSFA [5] are NR VQA methods.”
Self-citationMulti-Dimensional Quality Assessment for UGC Videos via Modular Multi-Modal Vision-Language Models
Zhang, W., Zheng, B., Chen, J., & Wang, Z. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00144 · Cited by 2
“UGC videos are often captured by users with varying photography skills, using different devices, and subject to unknown post-processing, compression, and transmission techniques before being uploaded to various platforms [37].”
Xu, L., Zhou, Y., Liu, S., Wen, F., Zhou, Y., Liu, X., Guo, J., Wang, Y., & Cao, J. (2025) · Displays · doi:10.1016/j.displa.2025.103221 · Cited by 1
Self-citationAi, D., He, T., Lu, M., Wang, D., & Liu, Y. (2025) · Displays · doi:10.1016/j.displa.2025.103259 · Cited by 3
Yu, R., & Hu, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131834 · Cited by 1
Perceiving Smoothness: Temporal Consistency Learning for Multi-Frame-Rate Video Quality Assessment
Han, J., Min, X., Sun, W., & Zhai, G. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209186
“Some [17]– [20] employ designed hand-crafted features to obtain spatial and motion information and improve some performance.”
ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos
Zhu, X., Duan, H., Yang, L., Zhu, Y., Min, X., Zhai, G., & Callet, P. L. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209505 · Cited by 12
“…ES-VQAnet, we compare it with 16 state-of-the-art no-reference (NR) VQA models designed for traditional 2D videos, which can be categorized into two groups: • Hand-crafted models: BRISQUE [22], BMPRI [20], NIQE [24], HOSA [23], BPRI-PSS [21], BPRI-LSSn [21], QAC [25], VIDEVAL [27], and TLVQM [26].”
Hu, B., Zhao, Y., Li, L., He, L., Lu, W. B., & Gao, X. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11210013
“We compared MACA-VQA against twelve representative SOTA UGC-VQA methods, including: 1) traditional methods like TLVQM [25] and VIDEVAL [3]; and 2) deep learning-based methods such as VSFA [1], Patch-VQ [5], BVQA [26], SimpleVQA [6], FastVQA [11], Dover [13], HVS-5M [27], PTM-VQA [28], KSVQE [29],…”
Exploring Cross-Modal Mutual Prompt Learning for Video Quality Assessment
Chen, P., Li, L., Wu, J., Yan, J., Jakhetiya, V., & Chetouani, A. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3639890 · Cited by 1
Subjective and Objective Quality Assessment of Display Content Videos
Huang, Y., Lu, F., Yu, H., Zhang, K., Sun, W., Min, X., & Zhai, G. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3642689
“…VQA models (VIIDEO [5], HIGRADE [55], FRIQUEE [56]). b) Deep Learning-Based Methods: General VQA models (TLVQM [30], RAPIQUE [33], VSFA [8], SimpleVQA [36], FastVQA [37], DOVER [17], ModularBVQA [18]) and specialized VQA models (FAVER [57], VIDEVAL [31], COVER [58], SAMA [59], Q-align [60]).”
No-reference video quality assessment based on spatio-temporal perception information
Shi, Z., & Wu, X. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113491
Visual fixation guided spatio-temporal dual branch network for gaming video quality assessment
Bai, M., Cui, Z., Lu, Z., Gan, Z., Tang, G., & Liu, F. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02123-7
“The representative VQA models for general videos include BRISQUE [3], TLVQM [4], VIDEVAL [5], RAPIQUE [8], VSFA [6], and FAST-VQA [19].”
EyeSim-VQA: A Free-Energy-Guided Eye Simulation Framework for Video Quality Assessment
Wang, Z., Lu, W. B., Li, J., He, L., Gong, M., & Gao, X. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3651537 · Cited by 1
“These include traditional methods (VIQE [59], TLVQM [42], RAPIQUE [60], VIDEVAL [43]), deep learning-based models (VSFA [18], GSTVQA [35], PVQ [9], FAVER [61], SimpleVQA [62], BVQA [63], FastVQA [19], FasterVQA [20], DOVER [21], PTM-VQA [64], ModularVQA [65]), and recent LLM-driven methods…”
Objective Quality Assessment of AI-Generated Content Videos With Transformation Consistency Focus
Xu, X., Wu, L., Yan, J., & Fang, Y. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3651308 · Cited by 3
“Although current VQA models can detect temporal inconsistency [5], [6], [7], [8], they are more focused on low-level distortions such as blurriness or jittering.”
RAM-VQA: Restoration Assisted Multi-Modality Video Quality Assessment
Chen, P., Yan, J., Soundararajan, R., Valenzise, G., Li, C., & Li, L. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3655117 · Cited by 1
“Further developments integrated complementary feature types, with TLVQM [15] incorporating both spatial high-complexity and temporal low-complexity characteristics, and VIDEVAL [16] employing feature fusion and selection to construct an ensemble prediction model.”
SCCOME: Scene Change Capture and Optical Motion Estimation for Video Quality Assessment
Liu, T.-J., Liao, H.-S., & Liu, K.-H. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343375
“VIDEVAL [16] performs feature selection from a pool of 763 candidate features and finally integrates the 60 most informative features to solve various UGC distortion problems.”
InfluentialGuan, F., Yu, Z., Lu, Y., Luo, W. H., Gao, Y., Li, X., & Chen, Z. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00366
“Traditional Video Quality Assessment (VQA) methods [13, 15, 19, 20, 25, 26] rely on handcrafted features for evaluating video quality.”
Light-VQA+: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidance
Zhou, X., Liu, X., Dong, Y., Kou, T., Gao, Y., Zhang, Z., Li, C., Wu, H., & Zhai, G. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02706-x · Cited by 12
Huang, M., Zhang, Y., Chandler, D. M., Leszczuk, M., & Farias, M. C. Q. (2026) · Journal on Image and Video Processing · doi:10.1186/s13640-026-00687-6 · Cited by 1
Kwong, N.-W., Chan, Y., Huang, Z., & Tsang, S. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3674552
“…[13], [14], [15], [16], [17], audio quality assessment (AQA) [18], [19], [20], [21], [22], and video quality assessment (VQA) [23], [24], [25], [26], [27], [28], [29], [30], [31], [32] over recent decades, these approaches predominantly focus on single-mode assessments that evaluate either…”
Efficient No-Reference Video Quality Assessment Using Video Masked Autoencoder Feature Mixing
Suresh, N., & Channappayya, S. S. (2025) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf67917.2025.11443711
“VIDeo quality EVALu-ator VIDEVAL) [9] effectively balances the trade-off between VQA performance and efficiency.”
Liang, Z., Sheng, W., Ma, H., Zhou, F., & Qiu, G. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3679733
“Early no reference (NR) VQA models are mainly based on handcrafted features and also known as traditional models [2], [3], [4], [24], [25].”
Yue, Y., & Qu, P. (2026) · Scientific Reports · doi:10.1038/s41598-026-38934-5 · Cited by 2
“Meanwhile, Tu et al. 36 stated that choir members with experience in singing advanced songs exhibit higher aesthetic responses compared to those without choir experience.”
Khan, Z. A. (2021) · theses.fr (ABES) · doi:10.70675/75d15fa7z97c5z418cza3b3z8f75630fddaa · Cited by 2
Deep learning-assisted video list decoding in error-prone video transmission systems
Zhang, Y. (2024) · theses.fr (ABES) · doi:10.70675/1d0878eez4905z432az9623zbee74e1a454f
Ganavdiya, S., Mogasati, R. S., Appina, B., et al. (2026) · Displays · doi:10.1016/j.displa.2026.103468
Zhou, Y., Zhang, Z., Wen, F., Xu, L., Zhang, Y., Zhou, Y., Cao, J., Shi, Y., Liu, X., Min, X., et al. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104817
Self-citation
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.