End-to-End Blind Quality Assessment of Compressed Videos Using Deep Neural Networks
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Blind video quality assessment (BVQA) algorithms are traditionally designed with a two-stage approach - a feature extraction stage that computes typically hand-crafted spatial and/or temporal features, and a regression stage working in the feature space that predicts the perceptual quality of the video. Unlike the traditional BVQA methods, we propose a Video Multi-task End-to-end Optimized neural Network (V-MEON) that merges the two stages into one, where the feature extractor and the regressor are jointly optimized. Our model uses a multi-task DNN framework that not only estimates the perceptual quality of the test video but also provides a probabilistic prediction of its codec type. This framework allows us to train the network with two complementary sets of labels, both of which can be obtained at low cost. The training process is composed of two steps. In the first step, early convolutional layers are pre-trained to extract spatiotemporal quality-related features with the codec classification subtask. In the second step, initialized with the pre-trained feature extractor, the whole network is jointly optimized with the two subtasks together. An additional critical step is the adoption of 3D convolutional layers, which creates novel spatiotemporal features that lead to a significant performance boost. Experimental results show that the proposed model clearly outperforms state-of-the-art BVQA methods.The source code of V-MEON is available at https://ece.uwaterloo.ca/~zduanmu/acmmm2018bvqa.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Large-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354 · cited 3×
“With data augmentation techniques [10, 19], we obtain tens of millions of training samples, providing a solid foundation for the training process.”
BackgroundMethodSpatial and Temporal Contrast-Sensitivity Functions of the Visual System
Robson, J. G. (1966) · Journal of the Optical Society of America · doi:10.1364/josa.56.001141 · Cited by 839
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 6×
“Normally, NVS features are first extracted [14, 15, 29, 40], and then a regression function is learned to map extracted features to quality scores.”
BackgroundMethodInfluentialA 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 5×
“We compare the average processing speed of V-BLIINDS [29], VIIDEO [21], and the proposed V-MEON-SF on the CSIQVQA [38] database, where all the videos have the same spatial resolution of 832 × 480.”
BackgroundMethodInfluentialMotion-induced blindness in normal observers
Bonneh, Y. S., Cooperman, A., & Sagi, D. (2001) · Nature · doi:10.1038/35081073 · Cited by 299 · cited 1×
“However, such a framework fails to take into account the following influencing factors in video perceptual quality: 1) motion-induced blindness [5, 28] to spatial distortions; 2) possible temporal artifacts or incoherence [29, 43]; 3) codec-specific distortions [43]; and 4) interactions between spatial and temporal ar…”
BackgroundViS3: an algorithm for video quality assessment via analysis of spatial and spatiotemporal slices
Vu, P. V., & Chandler, D. M. (2014) · Journal of Electronic Imaging · doi:10.1117/1.jei.23.1.013016 · Cited by 185 · cited 7×
“Table 1: SRCC and PLCC results on CSIQVQA [38]”
BackgroundMethodInfluential
Cited by
Quality 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
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
Tu, Z., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3072221 · Cited by 363
“The V-MEON model [72] used a multi-task CNN framework which jointly optimizes a 3D-CNN for feature extraction and a codec classifier using fully-connected layers to predict video quality.”
MethodPerceptual 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
Barman, N., Jammeh, E., Ghorashi, S. A., & Martini, M. G. (2019) · IEEE Access · doi:10.1109/access.2019.2920477 · Cited by 71
Metadata
- Authors
- Liu, W., Duanmu, Z., & Wang, Z.
- Venue
- Proceedings of the 26th ACM international conference on Multimedia
- Publisher
- ACM
- Published
- 2018-10-15
- Pages
- 546-554
- OpenAlex
- W2895868297
- Cited by
- 122
- References
- 7
- FWCI
- 3.23
- Type
- conference paper
- Language
- en
- Open access
- closed
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.