A Deep Learning based No-reference Quality Assessment Model for UGC Videos
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
Quality assessment for User Generated Content (UGC) videos plays an important role in ensuring the viewing experience of end-users. Previous UGC video quality assessment (VQA) studies either use the image recognition model or the image quality assessment (IQA) models to extract frame-level features of UGC videos for quality regression, which are regarded as the sub-optimal solutions because of the domain shifts between these tasks and the UGC VQA task. In this paper, we propose a very simple but effective UGC VQA model, which tries to address this problem by training an end-to-end spatial feature extraction network to directly learn the quality-aware spatial feature representation from raw pixels of the video frames. We also extract the motion features to measure the temporal-related distortions that the spatial features cannot model. The proposed model utilizes very sparse frames to extract spatial features and dense frames (i.e. the video chunk) with a very low spatial resolution to extract motion features, which thereby has low computational complexity. With the better quality-aware features, we only use the simple multilayer perception layer (MLP) network to regress them into the chunk-level quality scores, and then the temporal average pooling strategy is adopted to obtain the video-level quality score. We further introduce a multi-scale quality fusion strategy to solve the problem of VQA across different spatial resolutions, where the multi-scale weights are obtained from the contrast sensitivity function of the human visual system. The experimental results show that the proposed model achieves the best performance on five popular UGC VQA databases, which demonstrates the effectiveness of the proposed model.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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
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
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 1×
“Moreover, previous studies indicate that the features extracted by the shallow layers of the CNN models contain low-level information [28, 48], which responds to low-level features such as edges, corners, textures, etc.”
BackgroundMaking 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×
“• IQAmodels: NIQE [24], BRISQUE [22], GM-LOG [41], VGG19 [27], ResNet50 [7], and KonCept512 [9].”
MethodInfluentialMultiscale 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 · cited 1×
“Some existing work [38][25][20] shows that considering the multi-scale characteristics can improve the performance of image quality assessment.”
BackgroundNo-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 4×
“• IQAmodels: NIQE [24], BRISQUE [22], GM-LOG [41], VGG19 [27], ResNet50 [7], and KonCept512 [9].”
MethodInfluentialSlowFast Networks for Video Recognition
Feichtenhofer, C., Fan, H., Malik, J., & He, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00630 · Cited by 4,007
KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment
Hosu, V., Lin, H., Sziranyi, T., & Saupe, D. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2967829 · Cited by 759 · cited 2×
“• IQAmodels: NIQE [24], BRISQUE [22], GM-LOG [41], VGG19 [27], ResNet50 [7], and KonCept512 [9].”
Blind Image Quality Assessment Using Joint Statistics of Gradient Magnitude and Laplacian Features
Xue, W., Mou, X., Zhang, L., Bovik, A. C., & Feng, X. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2355716 · Cited by 641 · cited 2×
“• IQAmodels: NIQE [24], BRISQUE [22], GM-LOG [41], VGG19 [27], ResNet50 [7], and KonCept512 [9].”
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 5×
“V-BLIINDS [26] is a spatio-temporal natural scene statistics (NSS) model for videos by quantifying the NSS feature of frame-differences and motion coherency characteristics.”
MethodInfluentialQuality Assessment of In-the-Wild Videos
Li, D., Jiang, T., & Jiang, M. (2019) · Proceedings of the 27th ACM International Conference on Multimedia · doi:10.1145/3343031.3351028 · Cited by 387
A 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×
“[23] propose a training-free blind VQA model named VIIDEO that exploits intrinsic statistics regularities of natural videos to quantify disturbances introduced due to distortions.”
BackgroundMethodTwo-Level Approach for No-Reference Consumer Video Quality Assessment
Korhonen, J. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2923051 · Cited by 354 · cited 6×
“For the NR VQA methods, the hand-crafted feature based NR VQA methods such as TLVQM and VIDEVAL achieve pretty well performance by incorporating the rich spatial and temporal quality features, such as NSS features, motion features, etc., but they are inferior to the deep learning based NR VQA methods due to the strong…”
BackgroundMethodInfluentialThe Konstanz natural video database (KoNViD-1k)
Hosu, V., Hahn, F., Jenadeleh, M., Lin, H., Men, H., Sziranyi, T., Li, S., & Saupe, D. (2017) · 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex.2017.7965673 · Cited by 343
YouTube UGC Dataset for Video Compression Research
Wang, Y., Inguva, S., & Adsumilli, B. (2019) · 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2019.8901772 · Cited by 282
A Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment
Tu, Z., Chen, C.-J., Chen, L.-H., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2020) · 2020 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip40778.2020.9191169 · Cited by 71 · cited 2×
“Thoughmany temporal pooling methods have been proposed in literature [32][15], we find that the temporal”
BackgroundMethod
Cited by
Perceptual video quality assessment: a survey
Min, X., Duan, H., Sun, W., Zhu, Y., & Zhai, G. (2024) · Science China Information Sciences · doi:10.1007/s11432-024-4133-3 · Cited by 218
Self-citationDeep neural network for blind visual quality assessment of 4K content
Lu, W., Sun, W., Min, X., Zhu, W., Zhou, Q., He, J., Wang, Q., Zhang, Z., Wang, T., & Zhai, G. (2023) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2022.3221689 · Cited by 60
Self-citationQu, B., Liang, X., Sun, S., & Gao, W. (2024) · arXiv · doi:10.48550/arxiv.2404.13573 · Cited by 44
Metadata
- Authors
- Sun, W., Min, X., Lu, W., & Zhai, G.
- Venue
- Proceedings of the 30th ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2022-10-10
- Pages
- 856-865
- OpenAlex
- W4225292576
- Cited by
- 240
- References
- 16
- FWCI
- 19.51
- Type
- conference paper
- Language
- en
- Open access
- green
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.