Two-Level Approach for No-Reference Consumer Video Quality Assessment
The DOI matches its Crossref record; 43 of the 48 references it cites were found in a registry or an index.
Abstract
Smartphones and other consumer devices capable of capturing video content and sharing it on social media in nearly real time are widely available at a reasonable cost. Thus, there is a growing need for no-reference video quality assessment (NR-VQA) of consumer produced video content, typically characterized by capture impairments that are qualitatively different from those observed in professionally produced video content. To date, most of the NR-VQA models in prior art have been developed for assessing coding and transmission distortions, rather than capture impairments. In addition, the most accurate NR-VQA methods known in prior art are often computationally complex, and therefore impractical for many real life applications. In this paper, we propose a new approach for learning-based video quality assessment, based on the idea of computing features in two levels so that low complexity features are computed for the full sequence first, and then high complexity features are extracted from a subset of representative video frames, selected by using the low complexity features. We have compared the proposed method against several relevant benchmark methods using three recently published annotated public video quality databases, and our results show that the proposed method can predict subjective video quality more accurately than the benchmark methods. The best performing prior method achieves nearly similar accuracy, but at substantially higher computational cost.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Temporal pooling is one of the most important, unresolved problems for video quality prediction [42], [60], [76], [82], [83].”
From UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2021) · cites this paper as [42]
In the citing paper
“The model currently achieves SOTA performance on three UGC video quality databases, CVD2014 [12], KoNViD-1k [10], and LIVE-Qualcomm [13], at a reasonably low complexity, as reported by the authors.”
From UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2021) · cites this paper as [42]
In the citing paper
“We observed in Section II-B that LIVE-VQC videos generally contain more (camera) motions than KoNViD-1k and YouTube-UGC, and TLVQM computes multiple motion relevant features.”
From UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2021) · cites this paper as [42]
In the citing paper
“TLVQM does require that a large set of parameters (around 30) be specified, which may affect performance on datasets or application scenarios it has not been exposed to.”
From UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2021) · cites this paper as [42]
Citations
Cites
Making 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 4×
“In the field of NR-IQA and NR-VQA, Support Vector Regression (SVR) is the most commonly used regression model [5], [9], [38], [39], [43], but also neural networks and Random Forest Regression (RFR) have been employed successfully [7], [8], [12], [46].”
BackgroundMethodInfluentialNo-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 3×
“In the field of NR-IQA and NR-VQA, Support Vector Regression (SVR) is the most commonly used regression model [5], [9], [38], [39], [43], but also neural networks and Random Forest Regression (RFR) have been employed successfully [7], [8], [12], [46].”
MethodNatural Image Statistics and Neural Representation
Simoncelli, E. P., & Olshausen, B. A. (2001) · Annual Review of Neuroscience · doi:10.1146/annurev.neuro.24.1.1193 · Cited by 2,460 · cited 1×
“between neighboring locations, as well as spatial and temporal frequencies, follow certain typical statistical distributions [37].”
BackgroundDesign of an image edge detection filter using the Sobel operator
Kanopoulos, N., Vasanthavada, N., & Baker, R. L. (1988) · IEEE Journal of Solid-State Circuits · doi:10.1109/4.996 · Cited by 1,212
No-reference perceptual quality assessment of JPEG compressed images
Wang, Z., Sheikh, H. R., & Bovik, A. C. (2003) · Proceedings. International Conference on Image Processing · doi:10.1109/icip.2002.1038064 · Cited by 834
Unsupervised feature learning framework for no-reference image quality assessment
Ye, P., Kumar, J., Kang, L., & Doermann, D. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247789 · Cited by 785
A no-reference objective image sharpness metric based on the notion of just noticeable blur (JNB)
Ferzli, R., & Karam, L. J. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2008.2011760 · Cited by 758
The Evolution of Video Quality Measurement: From PSNR to Hybrid Metrics
Winkler, S., & Mohandas, P. (2008) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2008.2000733 · Cited by 598
Blind Prediction of Natural Video Quality
Saad, M. A., Bovik, A. C., & Charrier, C. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2299154 · Cited by 471 · cited 4×
“In the field of NR-IQA and NR-VQA, Support Vector Regression (SVR) is the most commonly used regression model [5], [9], [38], [39], [43], but also neural networks and Random Forest Regression (RFR) have been employed successfully [7], [8], [12], [46].”
MethodInfluentialA Completely Blind Video Integrity Oracle
Mittal, A., Saad, M. A., & Bovik, A. C. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2502725 · Cited by 357 · cited 2×
“Pixel-based models use a raw video signal solely as an input [4]–[5], [7]–[10], [12], and hybrid models combine features from the bitstream with features extracted from the”
BackgroundMethod
Research works printed but not linked: 13
- 2011, Objective Multimedia Video Quality Measurement of HDTV for Digital Cable Television in the Presence of a Reduced Reference Signal
- 2016, Objective Perceptual Multimedia Video Quality Measurement of HDTV for Digital Cable Television in the Presence of a Full Reference
- 2012, Methodology for the Subjective Assessment of the Quality of Television Pictures
- 2010, Report on the validation of video quality models for high definition video content
- ghadiyaram, 2017, LIVE-Qualcomm Mobile in-Capture Video Quality Database
- hosu, 2017, KoNViD-1k Video Database
- korhonen, 2019, Two Level Video Quality Model (TlvQM)
- zheng, 2018, Source Code for Classical Biqa Methods
- 2018, Image & Video Quality Assessment Algorithms Laboratory for Image & Video Engineering the University of Texas in Austin
- 2018, Scikit-Learn Toolbox
- alpert, 1997, Subjective quality evaluation–the SSCQE and DSCQE methodologies, EBU Tech Rev, 271, 12
- 1999, Subjective video quality assessment methods for multimedia applications
- nuutinen, 2018, The CVD Video Database
Cited by
Items 101–200 of 351
Advances in artificial intelligence: a review for the creative industries
Anantrasirichai, N., Zhang, F., & Bull, D. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11494-w · Cited by 106
Assessment of Subjective and Objective Quality of Live Streaming Sports Videos
Shang, Z., Ebenezer, J. P., Bovik, A. C., Wu, Y., Wei, H., & Sethuraman, S. (2021) · Picture Coding Symposium · doi:10.1109/pcs50896.2021.9477502 · Cited by 16
“However, the overall performance of CORNIA was lower than that of V-BLIINDS, TLVQM, and ChipQA-0, due to the lack of temporal information, e.g., when processing frame drops, TLVQM was able to effectively capture the perceptual effects of frame drops, but its performance drops on the compression and flicker distortions.”
MethodInfluentialZhou, Y., Zhang, Z., Wu, S., Jia, J., Jiang, Y., Sun, W., Liu, X., Min, X., & Zhai, G. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104321 · Cited by 18
Making Video Quality Assessment Models Robust to Bit Depth
Ebenezer, J. P., Shang, Z., Wu, Y., Wei, H., Sethuraman, S., & Bovik, A. C. (2023) · IEEE Signal Processing Letters · doi:10.1109/lsp.2023.3268602 · Cited by 12
Geometry-Aware Video Quality Assessment for Dynamic Digital Human
Zhang, Z., Zhou, Y., Sun, W., Min, X., & Zhai, G. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222061 · Cited by 16
“To incorporate spatial and temporal features, handcrafted-based methods have been proposed, such as VIIDEO [5], V-BLIINDS [6], TLVQM [7], and VIDEVAL [8].”
MethodDeep Learning Approach for No-Reference Screen Content Video Quality Assessment
Kwong, N.-W., Chan, Y., Tsang, S., Huang, Z., & Lam, K. (2024) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2024.3374042 · Cited by 12
“Also, CNN-TLVQM [15] combines the handcrafted human visual system features extracted from TLVQM [37] and the spatial features obtained from a pre-trained CNN via transfer learning.”
MethodNo-reference video quality assessment based on modeling temporal-memory effects
Pan, D., Wang, X., Shi, P. A., & Yu, S. (2021) · Displays · doi:10.1016/j.displa.2021.102075 · Cited by 14
No-Reference Video Quality Assessment Using Distortion Learning and Temporal Attention
Kossi, K. K., Coulombe, S., Desrosiers, C., & Gagnon, G. (2022) · IEEE Access · doi:10.1109/access.2022.3167446 · Cited by 13
“Note that * are performances taken from paper [38] and † from the methods’ original papers.”
MethodResultInfluentialQuality Feature Learning via Multi-Channel CNN and GRU for No-Reference Video Quality Assessment
Kwong, N.-W., Chan, Y., Tsang, S., & Lun, D. P.-K. (2023) · IEEE Access · doi:10.1109/access.2023.3259101 · Cited by 12
“Then, under the same experiment scheme, the SROCC performance was compared with TLVQM [10], VSFA [12], CNN-TLVQM [13], and LSCT-PHIQNet [30].”
BackgroundMethodInfluentialSurveillance Video Quality Assessment Based on Quality Related Retraining
Zhang, Z., Lu, W. J., Sun, W., Min, X., Wang, T., & Zhai, G. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897249 · Cited by 16
“Then V-BLIINDS2 [9] and TLVQM [10] use the spatio-temporal features to improve the understanding of video quality.”
MethodToward Efficient Video Compression Artifact Detection and Removal: A Benchmark Dataset
Lin, L., Wang, M., Yang, J., Zhang, K., & Zhao, T. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3414549 · Cited by 11
DVL2021: An ultra high definition video dataset for perceptual quality study
Xing, F., Wang, Y., Wang, H., He, J., & Yuan, J. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103374 · Cited by 12
Enhancing blind video quality assessment with rich quality-aware features
Sun, W., Cao, L., Jia, J., Zhang, Z., Zhang, Z., Min, X., & Zhai, G. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130452 · Cited by 39
“Knowledge-driven BVQA models [5,12,29,35,43,44] utilize carefully designed handcrafted features to quantify the video quality.”
InfluentialCoSTA: Co-training spatial–temporal attention for blind video quality assessment
Xing, F., Wang, Y., Tang, W., Zhu, G., & Kwong, S. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124651 · Cited by 13
Predicting Spatio-Temporal Entropic Differences for Robust No Reference Video Quality Assessment
Mitra, S., Soundararajan, R., & Channappayya, S. S. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3049682 · Cited by 9
“Benchmarking algorithms: We compare our model against state of the art NR VQA algorithms such as VBLIINDS [4], TLVQM [7], NSTSS [17], VSFA [6] and DeepVQA [23].”
BackgroundMethodInfluentialWu, W., Hu, S., Xiao, P., Deng, S., Li, J., Chen, Y., & Li, K. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00183 · Cited by 13
“In order to conduct a comprehensive assessment of the proposed method’s performance, we compare it with several popularly quality assessment models, namely BRISQUE [26], TLVQM [17], VIDEVAL [36], RAPIQUE [37], VSFA [20], PVQ [44], BVQA [19], and SimpleVQA [35].”
BackgroundMethodInfluentialBVI-VFI: A Video Quality Database for Video Frame Interpolation
Danier, D., Zhang, F., & Bull, D. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3327912 · Cited by 19
“These include image models, NIQE [116], BRISQUE [117] and deepIQA-NR [113], and video models, VIIDEO [118], VBLIINDS [119], VIDEVAL [120], RAPIQUE [121], ChipQA [122], TLVQM [123], FastVQA [124] and FAVER [78].”
Method360° video quality assessment based on saliency-guided viewport extraction
Yang, F., Yang, C., An, P., & Huang, X. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01285-0 · Cited by 12
“TLVQM [20] extracts low-complexity features from full video sequences and high-complexity features from representative frames for perceptual quality modeling.”
HIDRO-VQA: High Dynamic Range Oracle for Video Quality Assessment
Saini, S., Saha, A., & Bovik, A. C. (2024) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00056 · Cited by 16
“We conducted a performance evaluation of popular NSS-based NR-VQA models, including BRISQUE [39], HIGRADE [26], TLVQM [25], V-BLIINDS [48], HDR BVQM [3], VSFA [29], RAPIQUE [60], ChipQA [12], and HDR-ChipQA [13], alongside the popular self-supervised SDR pre-trained models such as CONTRIQUE, Re-IQA, and CONVIQT, using…”
MethodInfluentialHDR or SDR? A Subjective and Objective Study of Scaled and Compressed Videos
Ebenezer, J. P., Shang, Z., Chen, Y., Wu, Y., Wei, H., Sethuraman, S., & Bovik, A. C. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3404890 · Cited by 15
“TLVQM [34] explicitly models common distortions such as compression, blur, and flicker, using a variety of spatial and temporal filters and heuristics.”
MethodInfluentialFOVQA: Blind Foveated Video Quality Assessment
Jin, Y., Patney, A., Webb, R., & Bovik, A. C. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3185738 · Cited by 12
“Among the compared NR VQA algorithms, we included BRISQUE [22], SVBRISQUE [39], NIQE [23], V-BLIINDS [26], TLVQM [29], and the proposed FOVQA algorithm.”
MethodInfluentialEfficient User-Generated Video Quality Prediction
Tu, Z., Chen, C.-J., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · Picture Coding Symposium · doi:10.1109/pcs50896.2021.9477483 · Cited by 15
Video Quality Assessment of User Generated Content: A Benchmark Study and a New Model
Tu, Z., Chen, C.-J., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506189 · Cited by 14
“For practical reasons, we selected the initial feature candidates from BRISQUE [8], GM-LOG [40], HIGRADE [10], FRIQUEE [11], and TLVQM [12], which we group by feature attributes as BRISQUE, GM-( We calculated these spatial features every second frame within each non-overlapping one-second chunk,…”
MethodInfluentialAudio-Visual Quality Assessment for User Generated Content: Database and Method
Cao, Y., Min, X., Sun, W., Zhang, X.-P. S., & Zhai, G. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222476 · Cited by 10
“We utilize the following handcrafted video and audio feature extractors: • Video: BRISQUE [12], CORNIA [13], V-BLIINDS [14], TLVQM [15], VIDEVAL [16], and RAPIQUE [17].”
MethodVideo Quality Assessment for Online Processing: From Spatial to Temporal Sampling
Yan, J., Wu, L. T., Fang, Y., Liu, X., Xia, X., & Liu, W. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3450085 · Cited by 15
“Korhonen et al. [20] extracted a set of handcrafted spatio-temporal features to predict the quality of videos.”
No-Reference Video Quality Assessment Using Transformers and Attention Recurrent Networks
Kossi, K. K., Coulombe, S., & Desrosiers, C. (2024) · IEEE Access · doi:10.1109/access.2024.3468336 · Cited by 10
“Recent popular handcrafted methods include ChipQA [16], TLVQM [17] and VIDEVAL [18].”
MethodResultDelving 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 27
GLDBF: Global and local dual-branch fusion network for no-reference point cloud quality assessment
Chen, Z., Xiao, S., Wang, Y., Wang, Y., & Cai, H. (2024) · Displays · doi:10.1016/j.displa.2024.102882 · Cited by 10
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 12
“TLVQM [39] improves regression accuracy by extracting rich spatio-temporal features at two levels for training SVR models.”
Zhou, Y., Zhang, Z., Sun, W., Min, X., & Zhai, G. (2025) · Signal Processing Image Communication · doi:10.1016/j.image.2025.117371 · Cited by 11
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 22
Mitra, S., & Soundararajan, R. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548064 · Cited by 13
“TLVQM [16] deploys low complexity and high complexity features from video frames based on spatial, and temporal statistics of videos.”
BackgroundMethodResultInfluentialVarga, D. (2022) · Sensors · doi:10.3390/s22249696 · Cited by 9
“The two-level video quality model (TVLQM) proposed by Korhonen [36] first computed low-complexity features from the entire video sequence before the extraction of high-complexity features.”
MethodDynamic 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 12
“…which means the 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…”
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 13
“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).”
BackgroundMethodBH-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
“• BVQA: VIDEVAL [26], TLVQM [27], RAPIQUE [28], VSFA [14], BVQA 2D [7], BVQA 2D+3D [11], and FASTVQA [29].”
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.”
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
“…• IQA methods (8): BRISQUE [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…”
No-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
“For the final feature extraction, we utilized a multiscale feature extraction module to extract features after the last three max-pooling operations, inspired by algorithms such as GMSD [16], VSFA [7], and TLVQM [26], which enrich the feature set by average and standard deviation pooling of frame-level features.”
MethodKnowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos
Mitra, S., & Soundararajan, R. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i5.28221 · Cited by 13
An 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 15
“TLVQM [13] is a two-level no-reference VQA framework, which first computes low-complexity motion and spatial features across the entire video , and then extracts high-complexity features from representative frames, followed by SVR or RFR regression to evaluate quality scores.”
InfluentialHuman-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.”
Critical analysis on the reproducibility of visual quality assessment using deep features
Götz-Hahn, F., Hosu, V., & Saupe, D. (2022) · PLoS ONE · doi:10.1371/journal.pone.0269715 · Cited by 16
“The previous best-reported performance on KoNViD-1k had been achieved by TLVQM [23], with a 0.”
MethodInfluentialFull-Reference And No-Reference Quality Assessment For Compressed User-Generated Content Videos
Yang, L., Feng, L., Xu, J., Zhang, T., Liao, Y., & Li, J. (2021) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew53276.2021.9456013 · Cited by 13
Texture Information Boosts Video Quality Assessment
Zhang, A., & Wang, Y. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747546 · Cited by 10
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 9
Vishwakarma, A. K., & Bhurchandi, K. M. (2022) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103676 · Cited by 8
HDR-ChipQA: No-reference quality assessment on High Dynamic Range videos
Ebenezer, J. P., Shang, Z., Wu, Y., Wei, H., Sethuraman, S., & Bovik, A. C. (2024) · Signal Processing Image Communication · doi:10.1016/j.image.2024.117191 · Cited by 12
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
Mi, Y., Shu, Y., Li, Y., Chen, H., Zhou, P., & Liu, S. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680930 · Cited by 17
“TLVQM [22] considers two levels of features, first computing low complexity features for each frame to extract frame-level statistical features related to motion, and then computing high complexity features related to spatial distortion for representative frames.”
KVQ: 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 23
“Indeed, there are differences in the quality of disparate spatiotemporal regions within a video due to their distinct textures and distortions ( e.g. , motion blur, compression), and it may not align with the global perceptual quality [30].”
Ying, Z., Pan, D., & Shi, P. A. (2023) · Sensors · doi:10.3390/s23031511 · Cited by 8
“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”
MethodInfluentialPUGCQ: A Large Scale Dataset for Quality Assessment of Professional User-Generated Content
Guo, L., Chen, B., Zhu, L., He, Q., Fan, H., & Wang, S. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475183 · Cited by 10
“The Low Complexity Features (LCF) and High Complexity Features (HCF) were extracted in [16] and the results show that the combination of the two-level features could obtain desirable performance on different video quality databases.”
BackgroundStudy 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
“As for video quality assessment algorithms, VIIDEO[1], VBLIINDS[2], TLVQM[3], VSFA[8], CNN-TLVQM[54], RAPIQUE[55], VIDEVAL[56] are included.”
MethodInfluentialVisual 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 8
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 7
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
“The scores obtained from subjective methods are often taken as the ground truth of objective evaluation during the training process [2].”
MethodResultInfluentialNo-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 9
“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]).”
BackgroundMethodA Quality-of-Experience Database for Adaptive Omnidirectional Video Streaming
Liu, X., Yan, J., Wan, Z., Fang, Y., & Wang, Z. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3300529 · Cited by 8
A Perspective on Quality Evaluation for AI-Generated Videos
Zhang, Z., Sun, W., & Zhai, G. (2025) · Sensors · doi:10.3390/s25154668 · Cited by 11
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
“Thus, we focus on recent heuristic and pre-trained CNN based methods such as TLVQM [19], which comprises of motionbased features predominantly, VIDEVAL [48], which is a combination of various classical VQA and image QA feature based methods [11, 19, 33], and VSFA [22] which has a pre-trained ResNet50 [14] backbone.”
BackgroundMethodInfluentialTQP: 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 6
“Korhonen 24 proposes the TLVQM method, which represents temporal information using low-complexity features and spatial information using high-complexity features.”
InfluentialSB-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 FUNQUE Approach to the Quality Assessment of Compressed HDR Videos
Venkataramanan, A. K., Stejerean, C., Katsavounidis, I. X., et al. (2024) · Picture Coding Symposium · doi:10.1109/pcs60826.2024.10566413 · Cited by 6
“…was refined in [15]. resulting in the FUNQUE+ suite of models, by the use of a variety of Contrast Sensitivity Functions (CSFs), and by adapting existing quality models to be computed in the unified transform space, including VIF [19], ST-RRED [20], and the Spatial Activity Index (SAI) [21].”
MethodSun, W., Cao, L., Fu, K., Zhu, D., Jia, J., Hu, M., Min, X., & Zhai, G. (2025) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew68306.2025.11152231 · Cited by 10
Subjective and no-reference quality metric of domain independent images and videos
Lodha, I. (2021) · Computers & Graphics · doi:10.1016/j.cag.2021.01.013 · Cited by 5
An Innovative Video Quality Assessment Method and An Impairment Video Dataset
Shi, H., & Liu, C. (2021) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist50367.2021.9651418 · Cited by 5
Dynamic strategy to use optimum memory space in real-time video surveillance
Biswas, T., Bhattacharya, D., & Mandal, G. (2023) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-023-04521-z · Cited by 6
“The no-reference (NR) approaches (Yan et al. 2021; Korhonen 2019; Freitas et al. 2018; Oszust et al. 2020) are utilized to evaluate the quality-based assessment of our proposed method with state-of-the-art techniques because the ground truth of all the output frames is completely unknown.”
MethodNo-Reference Video Quality Assessment Using Voxel-Wise fMRI Models of the Visual Cortex
Mahankali, N. S., Raghavan, M., & Channappayya, S. S. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3136487 · Cited by 5
Sun, W., Wang, T., Min, X., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.01111 · Cited by 5
“For example, traditional hand-crafted feature based models [10][11] extract the low-level visual features, but it is difficult to understand the video content, while recent deep learning based methods [13][14] utilize the pretrained semantic features but ignore the effect of low-level visual…”
InfluentialMonotonic and Invertible Network: A General Framework for Learning IQA Model from Mixed Datasets
Chen, B., Xiao, K., Xuelin, S., & Wang, S. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02565-6 · Cited by 10
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
Efficient 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
“TLVQM [94] model captures artifacts such as camera shakiness, overexposure, underexposure, and sensor noise in UGC videos.”
ADS-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
“Korhonen et al. [21] proposed a two-level approach for no-reference consumer video quality assessment (TLVQM) that extracts initial feature extraction from video images and selects significant feature images for deep feature extraction.”
BackgroundMotion 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 5
“Most existing BVQA models capture temporal distortion-aware features by leveraging expensive between-frame motion vectors [17], complex analysis of wavelet filters [8, 18, 28], or simple statistics of adjacent frame-differences [1, 7].”
MethodInfluentialA Genetic Algorithm-based Image Enhancement Approach for Autonomous Driving at Night
Chen, X., Han, P., Huang, Y., et al. (2023) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb58369.2023.10211326 · Cited by 4
“There are various metrics to evaluate the performance of enhanced images, including entropy [20], mean gradient [21], contrast [22], PSNR (Peak Signal-to-Noise Ratio) [23], etc.”
BackgroundIntegrates 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
“Conventional VQA models commonly depend on hand-crafted features [2], [3], [4].”
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 7
“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.”
BackgroundOptimized 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
InternVQA: Advancing Compressed Video Quality Assessment with Distilling Large Foundation Model
Guan, F., Yu, Z., Lu, Y., et al. (2025) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas56072.2025.11044175 · Cited by 3
“Traditional methods[Mittal et al., 2015, Liao et al., 2022, Korhonen, 2019] rely on manually designed features to assess video quality; however, due to the limitations of handcrafted features, these methods typically only capture shallow quality representations and fail to account for the complex…”
Quality Aware Features for Performance Prediction and Time Reduction in Video Object Tracking
Nieto, R. G., Ruiz-Muñoz, J. F., Beron, J., Franco, C. A. A., Benítez-Restrepo, H. D., & Bovik, A. C. (2022) · IEEE Access · doi:10.1109/access.2022.3145799 · Cited by 5
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.”
MethodOn 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
“However, most of state-of-the-art NR methods [8, 22, 21, 9, 26] mainly focus on user-generated content (UGC), due to the vast availability of public benchmarks.”
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.”
InfluentialFeature 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
“They extract these spatial features from every other frame in successive, non-overlapping slices of one second, drawing inspiration from the effectiveness of standard deviation integration as initially introduced in GMSD [7] and later employed in TLVQM [10].”
Multiple Image Distortion DNN Modeling Individual Subject Quality Assessment
Tiotsop, L. F., Servetti, A., Počta, P., Wallendael, G. V., Barkowsky, M., & Masala, E. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3664198 · Cited by 4
Merging Multiple Datasets for Improved Appearance-Based Gaze Estimation
Wu, L., & Shi, B. E. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78341-8_6 · Cited by 6
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
“A two-level feature extraction mechanism is employed by TLVQM [32], where high- and low-level features are extracted from the whole sequence and a subset of representative sequences, respectively.”
InfluentialA 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 5
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
Metadata
- Authors
- Korhonen, J.
- Affiliations
- Shenzhen University (CN)
- Corresponding author
- Korhonen, Jari
- ORCID
- Korhonen, Jari
- Venue
- IEEE Transactions on Image Processing
- Published
- 2019-12
- Volume
- 28
- Issue
- 12
- Pages
- 5923-5938
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2950154603
- Semantic Scholar
- f441c421b710c164872298679de173621dc980dc
- Cited by
- 354
- References
- 48
- Citations by year
- 2026: 38 · 2025: 67 · 2024: 65 · 2023: 72 · 2022: 48 · 2021: 53 · 2020: 10 · 2019: 1
- FWCI
- 12.53
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (61772348)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- no-reference video quality assessment, consumer video, representative frame selection, computational efficiency
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.
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.