pith. sign in

arxiv: 2409.17596 · v3 · submitted 2024-09-26 · 💻 cs.MM · cs.AI· eess.IV

Subjective and Objective Quality-of-Experience Evaluation Study for Live Video Streaming

Zehao Zhu , Wei Sun , Jun Jia , Wei Wu , Sibin Deng , Kai Li , Ying Chen , Xiongkuo Min
show 2 more authors
Jia Wang Guangtao Zhai
This is my paper

Pith reviewed 2026-05-23 21:07 UTC · model grok-4.3

classification 💻 cs.MM cs.AIeess.IV
keywords live video streamingquality of experienceQoE datasetsubjective evaluationobjective QoE modelsemantic featuresoptical flowTao-QoE
0
0 comments X

The pith

An end-to-end model predicts retrospective QoE for live video streaming from semantic and motion features alone.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces TaoLive QoE, the first dataset built from 42 real live broadcast source videos and 1155 distorted versions that include live-specific issues such as frame skipping and variable frame rate, along with human-collected subjective scores. Benchmarking shows that existing QoE models, largely tuned on video-on-demand content, fail to assess live streams accurately. The authors therefore present Tao-QoE, which extracts multi-scale semantic features and optical flow motion features to output a retrospective QoE score directly from the video pixels. Service providers could thereby optimize live compression and transmission for viewer satisfaction without collecting or relying on network quality-of-service statistics.

Core claim

By releasing the TaoLive QoE dataset and showing the shortcomings of prior metrics on it, the work establishes that an end-to-end model called Tao-QoE, which fuses multi-scale semantic features with optical flow-based motion features, can predict retrospective QoE scores for live streaming without any statistical QoS inputs and performs competitively on both the new live dataset and existing VoD datasets.

What carries the argument

Tao-QoE, an end-to-end neural model that integrates multi-scale semantic features and optical flow-based motion features to produce a retrospective QoE score.

If this is right

  • Existing QoE models struggle to assess live video content accurately.
  • The TaoLive QoE dataset supplies the first public subjective ratings for live-specific distortions such as frame skipping.
  • Tao-QoE removes the need for statistical QoS features when estimating viewer experience.
  • The same feature combination can be benchmarked on both live and on-demand video datasets.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The approach could support QoE-driven decisions in settings where network statistics are unavailable or costly to obtain.
  • Retraining or fine-tuning the model on additional live sources might reveal how well the semantic-motion combination generalizes across platforms.
  • A real-time version of the same architecture could be tested for use inside adaptive streaming controllers.

Load-bearing premise

The distortions and subjective ratings collected in the TaoLive QoE dataset accurately represent real-world live streaming conditions, and semantic plus motion features alone are sufficient to predict QoE without QoS inputs.

What would settle it

Apply Tao-QoE and competing QoS-dependent models to a fresh collection of live streaming videos accompanied by new human subjective ratings; if Tao-QoE's prediction error rises substantially above the QoS-based models, the central claim does not hold.

Figures

Figures reproduced from arXiv: 2409.17596 by Guangtao Zhai, Jia Wang, Jun Jia, Kai Li, Sibin Deng, Wei Sun, Wei Wu, Xiongkuo Min, Ying Chen, Zehao Zhu.

Figure 1
Figure 1. Figure 1: Distortion in actual broadcast scenarios [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Stalling event, accelerated play and frame skipping in TaoLive QoE Database. [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Sample frames of the videos in the proposed TaoLive QoE [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Illustration of the proposed TaoLive QoE database’s MOS distributions from different perspectives [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: The overall structure of the proposed network. 1)semantic feature extraction sub-network to extract semantic features from individual [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: New criteria performance of 11 state-of-art FR and NR QoE models and our proposed model on WaterlooSQoE-IV database. (a) and [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
read the original abstract

In recent years, live video streaming has gained widespread popularity across various social media platforms. Quality of experience (QoE), which reflects end-users' satisfaction and overall experience, plays a critical role for media service providers to optimize large-scale live compression and transmission strategies to achieve perceptually optimal rate-distortion trade-off. Although many QoE metrics for video-on-demand (VoD) have been proposed, there remain significant challenges in developing QoE metrics for live video streaming. To bridge this gap, we conduct a comprehensive study of subjective and objective QoE evaluations for live video streaming. For the subjective QoE study, we introduce the first live video streaming QoE dataset, TaoLive QoE, which consists of $42$ source videos collected from real live broadcasts and $1,155$ corresponding distorted ones degraded due to a variety of streaming distortions, including conventional streaming distortions such as compression, stalling, as well as live streaming-specific distortions like frame skipping, variable frame rate, etc. Subsequently, a human study was conducted to derive subjective QoE scores of videos in the TaoLive QoE dataset. For the objective QoE study, we benchmark existing QoE models on the TaoLive QoE dataset as well as publicly available QoE datasets for VoD scenarios, highlighting that current models struggle to accurately assess video QoE, particularly for live content. Hence, we propose an end-to-end QoE evaluation model, Tao-QoE, which integrates multi-scale semantic features and optical flow-based motion features to predicting a retrospective QoE score, eliminating reliance on statistical quality of service (QoS) features.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 4 minor

Summary. The paper introduces the TaoLive QoE dataset (42 source videos from real broadcasts and 1,155 distorted versions covering compression, stalling, frame skipping, and variable frame rate), reports results from a human subjective study yielding QoE scores, benchmarks existing QoE models on this dataset and VoD datasets to show their limitations on live content, and proposes the Tao-QoE end-to-end model that combines multi-scale semantic features with optical flow-based motion features to predict retrospective QoE scores without any QoS inputs.

Significance. If the reported correlation metrics and ablations hold, the new live-specific dataset and the QoS-free model would address a clear gap in QoE assessment for live streaming, with the feature-based approach offering a potentially more generalizable alternative to QoS-dependent metrics.

minor comments (4)
  1. [§3] §3 (Dataset): provide the exact breakdown of distortion types and their frequencies across the 1,155 videos to allow readers to assess coverage of live-specific artifacts.
  2. [§7] §7 (Experiments): report the precise Pearson/Spearman correlation values, RMSE, and any statistical significance tests for Tao-QoE versus the benchmarked models on the held-out test set.
  3. [§6] §6 (Model): clarify the exact architecture for fusing multi-scale semantic features with optical-flow motion features (e.g., concatenation layer dimensions or attention mechanism) so the end-to-end claim can be reproduced.
  4. [Figure 4] Figure 4 (Ablation): add error bars or p-values to the bar plots showing contribution of semantic versus motion features.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the careful reading, positive assessment of the TaoLive QoE dataset and Tao-QoE model, and the recommendation of minor revision. No major comments were provided in the report.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper introduces a new dataset (TaoLive QoE) with subjective scores collected independently, then trains and evaluates Tao-QoE on held-out test data using multi-scale semantic and optical-flow features. The central claim—that retrospective QoE can be predicted without QoS inputs—is supported by standard correlation metrics and feature ablations that do not reduce to self-definition, fitted-input renaming, or load-bearing self-citation. No equation or step equates the output to its inputs by construction; the model is an independent predictor whose performance is externally falsifiable on the reported test set.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Based solely on the abstract; no explicit free parameters, axioms, or invented entities are described. The model is presented as feature-based without reference to fitted constants or new postulated entities.

pith-pipeline@v0.9.0 · 5852 in / 1188 out tokens · 70493 ms · 2026-05-23T21:07:16.468909+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. QoS-QoE Translation with Large Language Model

    cs.MM 2026-04 unverdicted novelty 6.0

    A new QoS-QoE Translation dataset is constructed from multimedia literature and fine-tuned LLMs demonstrate strong performance on bidirectional continuous and discrete QoS-QoE predictions.

Reference graph

Works this paper leans on

69 extracted references · 69 canonical work pages · cited by 1 Pith paper · 4 internal anchors

  1. [1]

    ”Streaming on twitch: fostering participatory communities of play within live mixed media.” Proceedings of the SIGCHI conference on human factors in computing systems

    Hamilton, William A., Oliver Garretson, and Andruid Kerne. ”Streaming on twitch: fostering participatory communities of play within live mixed media.” Proceedings of the SIGCHI conference on human factors in computing systems. 2014

    work page 2014

  2. [2]

    ”Why is multimedia quality of experience assessment a challenging problem?.” IEEE Access 7 (2019): 117897-117915

    Akhtar, Zahid, et al. ”Why is multimedia quality of experience assessment a challenging problem?.” IEEE Access 7 (2019): 117897-117915

    work page 2019

  3. [4]

    ”Qualinet white paper on definitions of quality of experience.” (2013)

    Brunnstr ¨om, Kjell, et al. ”Qualinet white paper on definitions of quality of experience.” (2013)

    work page 2013

  4. [5]

    ”Measuring the quality of experience of HTTP video streaming.” 12th IFIP/IEEE international symposium on integrated network management (IM 2011) and workshops

    Mok, Ricky KP, Edmond WW Chan, and Rocky KC Chang. ”Measuring the quality of experience of HTTP video streaming.” 12th IFIP/IEEE international symposium on integrated network management (IM 2011) and workshops. IEEE, 2011

    work page 2011

  5. [6]

    ”Assessing quality of experience for adaptive HTTP video streaming.” 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

    Xue, Jingteng, et al. ”Assessing quality of experience for adaptive HTTP video streaming.” 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW). IEEE, 2014

    work page 2014

  6. [7]

    ”A control-theoretic approach for dynamic adaptive video streaming over HTTP.” Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication

    Yin, Xiaoqi, et al. ”A control-theoretic approach for dynamic adaptive video streaming over HTTP.” Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication. 2015

    work page 2015

  7. [8]

    Channappayya

    Manasa, K., and Sumohana S. Channappayya. ”An optical flow-based full reference video quality assessment algorithm.” IEEE Transactions on Image Processing 25.6 (2016): 2480-2492

    work page 2016

  8. [9]

    ”Quality assessment for video with degradation along salient trajectories.” IEEE Transactions on Multimedia 21.11 (2019): 2738-2749

    Wu, Jinjian, et al. ”Quality assessment for video with degradation along salient trajectories.” IEEE Transactions on Multimedia 21.11 (2019): 2738-2749

    work page 2019

  9. [10]

    Bampis, Christos G., Zhi Li, and Alan C. Bovik. ”Spatiotemporal feature integration and model fusion for full reference video quality assessment.” IEEE Transactions on Circuits and Systems for Video Technology 29.8 (2018): 2256-2270

    work page 2018

  10. [11]

    Wang, Zhou, Ligang Lu, and Alan C. Bovik. ”Video quality assessment based on structural distortion measurement.” Signal processing: Image communication 19.2 (2004): 121-132

    work page 2004

  11. [12]

    ”Motion tuned spatio- temporal quality assessment of natural videos.” IEEE transactions on image processing 19.2 (2009): 335-350

    Seshadrinathan, Kalpana, and Alan Conrad Bovik. ”Motion tuned spatio- temporal quality assessment of natural videos.” IEEE transactions on image processing 19.2 (2009): 335-350

    work page 2009

  12. [13]

    Soundararajan, Rajiv, and Alan C. Bovik. ”Video quality assessment by reduced reference spatio-temporal entropic differencing.” IEEE Transac- tions on Circuits and Systems for Video Technology 23.4 (2012): 684- 694

    work page 2012

  13. [14]

    Simoncelli

    Wang, Zhou, and Eero P. Simoncelli. ”Reduced-reference image quality assessment using a wavelet-domain natural image statistic model.” Human vision and electronic imaging X. V ol. 5666. SPIE, 2005

    work page 2005

  14. [15]

    ”Reduced-reference image quality assessment using reorganized DCT-based image representation.” IEEE Transactions on multimedia 13.4 (2011): 824-829

    Ma, Lin, et al. ”Reduced-reference image quality assessment using reorganized DCT-based image representation.” IEEE Transactions on multimedia 13.4 (2011): 824-829

    work page 2011

  15. [16]

    ”Reduced-reference image quality assessment by structural similarity estimation.” IEEE transactions on image processing 21.8 (2012): 3378-3389

    Rehman, Abdul, and Zhou Wang. ”Reduced-reference image quality assessment by structural similarity estimation.” IEEE transactions on image processing 21.8 (2012): 3378-3389

    work page 2012

  16. [17]

    ”Empirical evaluation of no- reference VQA methods on a natural video quality database.” 2017 Ninth international conference on quality of multimedia experience (QoMEX)

    Men, Hui, Hanhe Lin, and Dietmar Saupe. ”Empirical evaluation of no- reference VQA methods on a natural video quality database.” 2017 Ninth international conference on quality of multimedia experience (QoMEX). IEEE, 2017

    work page 2017

  17. [18]

    ”Spatiotemporal feature com- bination model for no-reference video quality assessment.” 2018 Tenth international conference on quality of multimedia experience (QoMEX)

    Men, Hui, Hanhe Lin, and Dietmar Saupe. ”Spatiotemporal feature com- bination model for no-reference video quality assessment.” 2018 Tenth international conference on quality of multimedia experience (QoMEX). IEEE, 2018

    work page 2018

  18. [19]

    Li, Yuming, et al. ”No-reference video quality assessment with 3D shearlet transform and convolutional neural networks.” IEEE Transactions on Circuits and Systems for Video Technology 26.6 (2015): 1044-1057

    work page 2015

  19. [20]

    Bovik, and Christophe Charrier

    Saad, Michele A., Alan C. Bovik, and Christophe Charrier. ”Blind pre- diction of natural video quality.” IEEE Transactions on image Processing 23.3 (2014): 1352-1365

    work page 2014

  20. [21]

    ”No-reference video quality assessment via feature learning.” 2014 IEEE international conference on image processing (ICIP)

    Xu, Jingtao, et al. ”No-reference video quality assessment via feature learning.” 2014 IEEE international conference on image processing (ICIP). IEEE, 2014

    work page 2014

  21. [22]

    Saad, and Alan C

    Mittal, Anish, Michele A. Saad, and Alan C. Bovik. ”A completely blind video integrity oracle.” IEEE Transactions on Image Processing 25.1 (2015): 289-300. JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 13

    work page 2015

  22. [24]

    ”RIRNet: Recurrent-in-recurrent network for video quality assessment.” Proceedings of the 28th ACM international confer- ence on multimedia

    Chen, Pengfei, et al. ”RIRNet: Recurrent-in-recurrent network for video quality assessment.” Proceedings of the 28th ACM international confer- ence on multimedia. 2020

    work page 2020

  23. [25]

    Sitaraman

    Spiteri, Kevin, Rahul Urgaonkar, and Ramesh K. Sitaraman. ”BOLA: Near-optimal bitrate adaptation for online videos.” IEEE/ACM transac- tions on networking 28.4 (2020): 1698-1711

    work page 2020

  24. [26]

    Begen, and Roger Zimmermann

    Bentaleb, Abdelhak, Ali C. Begen, and Roger Zimmermann. ”SD- NDASH: Improving QoE of HTTP adaptive streaming using software defined networking.” Proceedings of the 24th ACM international confer- ence on Multimedia. 2016

    work page 2016

  25. [28]

    Bampis, Christos G., and Alan C. Bovik. ”Learning to predict stream- ing video QoE: Distortions, rebuffering and memory.” arXiv preprint arXiv:1703.00633 (2017)

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  26. [29]

    ”A knowledge-driven quality-of-experience model for adaptive streaming videos.” arXiv preprint arXiv:1911.07944 (2019)

    Duanmu, Zhengfang, et al. ”A knowledge-driven quality-of-experience model for adaptive streaming videos.” arXiv preprint arXiv:1911.07944 (2019)

    work page arXiv 1911

  27. [30]

    ”Quality of Experience Evaluation for Streaming Video Using CGNN.” 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)

    Zhou, Zhiming, et al. ”Quality of Experience Evaluation for Streaming Video Using CGNN.” 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP). IEEE, 2020

    work page 2020

  28. [31]

    ”From Whole Video to Frames: Weakly-Supervised Domain Adaptive Continuous-Time QoE Evaluation.” IEEE Transactions on Image Processing 31 (2022): 4937-4951

    Li, Leida, et al. ”From Whole Video to Frames: Weakly-Supervised Domain Adaptive Continuous-Time QoE Evaluation.” IEEE Transactions on Image Processing 31 (2022): 4937-4951

    work page 2022

  29. [32]

    ”DeSVQ: Deep learning based streaming video QoE estimation.” Proceedings of the 23rd International Conference on Distributed Computing and Networking

    Ghosh, Monalisa, Dr Chetna Singhal, and Rushikesh Wayal. ”DeSVQ: Deep learning based streaming video QoE estimation.” Proceedings of the 23rd International Conference on Distributed Computing and Networking. 2022

    work page 2022

  30. [33]

    ”Temporal reasoning guided QoE evaluation for mobile live video broadcasting.” IEEE Transactions on Image Processing 30 (2021): 3279-3292

    Chen, Pengfei, et al. ”Temporal reasoning guided QoE evaluation for mobile live video broadcasting.” IEEE Transactions on Image Processing 30 (2021): 3279-3292

    work page 2021

  31. [34]

    ”A bitstream-based, scalable video-quality model for HTTP adaptive streaming: ITU-T P

    Raake, Alexander, et al. ”A bitstream-based, scalable video-quality model for HTTP adaptive streaming: ITU-T P. 1203.1.” 2017 Ninth international conference on quality of multimedia experience (QoMEX). IEEE, 2017

    work page 2017

  32. [35]

    ”A quality-of-experience index for streaming video.” IEEE Journal of Selected Topics in Signal Processing 11.1 (2016): 154-166

    Duanmu, Zhengfang, et al. ”A quality-of-experience index for streaming video.” IEEE Journal of Selected Topics in Signal Processing 11.1 (2016): 154-166

    work page 2016

  33. [36]

    ”Quality-of-experience for adaptive streaming videos: An expectation confirmation theory moti- vated approach.” IEEE Transactions on Image Processing 27.12 (2018): 6135-6146

    Duanmu, Zhengfang, Kede Ma, and Zhou Wang. ”Quality-of-experience for adaptive streaming videos: An expectation confirmation theory moti- vated approach.” IEEE Transactions on Image Processing 27.12 (2018): 6135-6146

    work page 2018

  34. [37]

    ”A quality-of- experience database for adaptive video streaming.” IEEE Transactions on Broadcasting 64.2 (2018): 474-487

    Duanmu, Zhengfang, Abdul Rehman, and Zhou Wang. ”A quality-of- experience database for adaptive video streaming.” IEEE Transactions on Broadcasting 64.2 (2018): 474-487

    work page 2018

  35. [38]

    ”Assessing the quality-of-experience of adap- tive bitrate video streaming.” arXiv preprint arXiv:2008.08804 (2020)

    Duanmu, Zhengfang, et al. ”Assessing the quality-of-experience of adap- tive bitrate video streaming.” arXiv preprint arXiv:2008.08804 (2020)

    work page arXiv 2008

  36. [39]

    ”Study of temporal effects on subjective video quality of experience.” IEEE Transactions on Image Processing 26.11 (2017): 5217-5231

    Bampis, Christos George, et al. ”Study of temporal effects on subjective video quality of experience.” IEEE Transactions on Image Processing 26.11 (2017): 5217-5231

    work page 2017

  37. [40]

    Towards Perceptually Optimized End-to-end Adaptive Video Streaming

    Bampis, Christos G., et al. ”Towards perceptually optimized end-to-end adaptive video streaming.” arXiv preprint arXiv:1808.03898 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  38. [41]

    ”A real-time blind quality-of-experience assessment metric for HTTP adaptive streaming.” arXiv preprint arXiv:2303.09818 (2023)

    Li, Chunyi, et al. ”A real-time blind quality-of-experience assessment metric for HTTP adaptive streaming.” arXiv preprint arXiv:2303.09818 (2023)

    work page arXiv 2023

  39. [42]

    ”Methodology for the subjective assessment of the quality of television pictures.” International Telecommunication Union 4 (2002)

    BT, RIR. ”Methodology for the subjective assessment of the quality of television pictures.” International Telecommunication Union 4 (2002)

    work page 2002

  40. [43]

    ”Swin transformer: Hierarchical vision transformer using shifted windows.” Proceedings of the IEEE/CVF international conference on computer vision

    Liu, Ze, et al. ”Swin transformer: Hierarchical vision transformer using shifted windows.” Proceedings of the IEEE/CVF international conference on computer vision. 2021

    work page 2021

  41. [44]

    ”Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume.” Proceedings of the IEEE conference on computer vision and pattern recognition

    Sun, Deqing, et al. ”Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2018

    work page 2018

  42. [45]

    ”Can spatiotempo- ral 3d cnns retrace the history of 2d cnns and imagenet?.” Proceedings of the IEEE conference on Computer Vision and Pattern Recognition

    Hara, Kensho, Hirokatsu Kataoka, and Yutaka Satoh. ”Can spatiotempo- ral 3d cnns retrace the history of 2d cnns and imagenet?.” Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2018

    work page 2018

  43. [47]

    ”Low-complexity video quality assessment using temporal quality variations.” IEEE Transactions on Multimedia 14.3 (2012): 525-535

    Narwaria, Manish, Weisi Lin, and Anmin Liu. ”Low-complexity video quality assessment using temporal quality variations.” IEEE Transactions on Multimedia 14.3 (2012): 525-535

    work page 2012

  44. [48]

    ”Imagenet: A large-scale hierarchical image database.” 2009 IEEE conference on computer vision and pattern recognition

    Deng, Jia, et al. ”Imagenet: A large-scale hierarchical image database.” 2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009

    work page 2009

  45. [49]

    The Kinetics Human Action Video Dataset

    Kay, Will, et al. ”The kinetics human action video dataset.” arXiv preprint arXiv:1705.06950 (2017)

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  46. [50]

    Adam: A Method for Stochastic Optimization

    Kingma, Diederik P., and Jimmy Ba. ”Adam: A method for stochastic optimization.” arXiv preprint arXiv:1412.6980 (2014)

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  47. [51]

    ”Automatic differentiation in pytorch.” (2017)

    Paszke, Adam, et al. ”Automatic differentiation in pytorch.” (2017)

    work page 2017

  48. [52]

    Ghadiyaram, Deepti, et al. ”In-capture mobile video distortions: A study of subjective behavior and objective algorithms.” IEEE Transactions on Circuits and Systems for Video Technology 28.9 (2017): 2061-2077

    work page 2017

  49. [53]

    ”CVD2014—A database for evaluating no- reference video quality assessment algorithms.” IEEE Transactions on Image Processing 25.7 (2016): 3073-3086

    Nuutinen, Mikko, et al. ”CVD2014—A database for evaluating no- reference video quality assessment algorithms.” IEEE Transactions on Image Processing 25.7 (2016): 3073-3086

    work page 2016

  50. [54]

    ”The Konstanz natural video database (KoNViD-1k).” 2017 Ninth international conference on quality of multimedia experience (QoMEX)

    Hosu, Vlad, et al. ”The Konstanz natural video database (KoNViD-1k).” 2017 Ninth international conference on quality of multimedia experience (QoMEX). IEEE, 2017

    work page 2017

  51. [55]

    ”VDPVE: VQA Dataset for Perceptual Video Enhancement.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Gao, Yixuan, et al. ”VDPVE: VQA Dataset for Perceptual Video Enhancement.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023

    work page 2023

  52. [56]

    ”Video compression dataset and benchmark of learning-based video-quality metrics.” Advances in Neural Information Processing Systems 35 (2022): 13814-13825

    Antsiferova, Anastasia, et al. ”Video compression dataset and benchmark of learning-based video-quality metrics.” Advances in Neural Information Processing Systems 35 (2022): 13814-13825

    work page 2022

  53. [57]

    ”Large-scale study of perceptual video quality.” IEEE Transactions on Image Processing 28.2 (2018): 612- 627

    Sinno, Zeina, and Alan Conrad Bovik. ”Large-scale study of perceptual video quality.” IEEE Transactions on Image Processing 28.2 (2018): 612- 627

    work page 2018

  54. [58]

    ”YouTube UGC dataset for video compression research.” 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP)

    Wang, Yilin, Sasi Inguva, and Balu Adsumilli. ”YouTube UGC dataset for video compression research.” 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP). IEEE, 2019

    work page 2019

  55. [59]

    ”Predicting the quality of compressed videos with pre-existing distortions.” IEEE Transactions on Image Processing 30 (2021): 7511-7526

    Yu, Xiangxu, et al. ”Predicting the quality of compressed videos with pre-existing distortions.” IEEE Transactions on Image Processing 30 (2021): 7511-7526

    work page 2021

  56. [60]

    ”Multi-channel decomposition in tandem with free- energy principle for reduced-reference image quality assessment.” IEEE Transactions on Multimedia 21.9 (2019): 2334-2346

    Zhu, Wenhan, et al. ”Multi-channel decomposition in tandem with free- energy principle for reduced-reference image quality assessment.” IEEE Transactions on Multimedia 21.9 (2019): 2334-2346

    work page 2019

  57. [61]

    ”Objective quality evaluation of dehazed images.” IEEE Transactions on Intelligent Transportation Systems 20.8 (2018): 2879-2892

    Min, Xiongkuo, et al. ”Objective quality evaluation of dehazed images.” IEEE Transactions on Intelligent Transportation Systems 20.8 (2018): 2879-2892

    work page 2018

  58. [62]

    ”Quality evaluation of image dehazing methods using synthetic hazy images.” IEEE Transactions on Multimedia 21.9 (2019): 2319-2333

    Min, Xiongkuo, et al. ”Quality evaluation of image dehazing methods using synthetic hazy images.” IEEE Transactions on Multimedia 21.9 (2019): 2319-2333

    work page 2019

  59. [63]

    Krasula, Luk ´aˇs, et al. ”On the accuracy of objective image and video quality models: New methodology for performance evaluation.” 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX). IEEE, 2016

    work page 2016

  60. [64]

    ”How to benchmark objective quality metrics from paired comparison data?.” 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX)

    Hanhart, Philippe, et al. ”How to benchmark objective quality metrics from paired comparison data?.” 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX). Ieee, 2016

    work page 2016

  61. [65]

    ”Quality assessment of sharpened images: Chal- lenges, methodology, and objective metrics.” IEEE Transactions on Image Processing 26.3 (2017): 1496-1508

    Krasula, Luk ´aˇs, et al. ”Quality assessment of sharpened images: Chal- lenges, methodology, and objective metrics.” IEEE Transactions on Image Processing 26.3 (2017): 1496-1508

    work page 2017

  62. [66]

    ”Preference of experience in image tone-mapping: Dataset and framework for objective measures comparison.” IEEE Journal of Selected Topics in Signal Processing 11.1 (2016): 64-74

    Krasula, Luk ´aˇs, et al. ”Preference of experience in image tone-mapping: Dataset and framework for objective measures comparison.” IEEE Journal of Selected Topics in Signal Processing 11.1 (2016): 64-74

    work page 2016

  63. [67]

    ”Accuracy and cross-calibration of video quality metrics: new methods from ATIS/T1A1.” Signal Processing: Image Communication 19.2 (2004): 101-107

    Brill, Michael H., et al. ”Accuracy and cross-calibration of video quality metrics: new methods from ATIS/T1A1.” Signal Processing: Image Communication 19.2 (2004): 101-107

    work page 2004

  64. [68]

    Hanley, James A., and Barbara J. McNeil. ”A method of comparing the areas under receiver operating characteristic curves derived from the same cases.” Radiology 148.3 (1983): 839-843

    work page 1983

  65. [69]

    ”Two-level approach for no-reference consumer video quality assessment.” IEEE Transactions on Image Processing 28.12 (2019): 5923-5938

    Korhonen, Jari. ”Two-level approach for no-reference consumer video quality assessment.” IEEE Transactions on Image Processing 28.12 (2019): 5923-5938

    work page 2019

  66. [70]

    ”Quality assessment of in- the-wild videos.” Proceedings of the 27th ACM International Conference on Multimedia

    Li, Dingquan, Tingting Jiang, and Ming Jiang. ”Quality assessment of in- the-wild videos.” Proceedings of the 27th ACM International Conference on Multimedia. 2019

    work page 2019

  67. [71]

    ”A deep learning based no-reference quality assessment model for ugc videos.” Proceedings of the 30th ACM International Conference on Multimedia

    Sun, Wei, et al. ”A deep learning based no-reference quality assessment model for ugc videos.” Proceedings of the 30th ACM International Conference on Multimedia. 2022

    work page 2022

  68. [72]

    ”Fast-vqa: Efficient end-to-end video quality as- sessment with fragment sampling.” European Conference on Computer Vision

    Wu, Haoning, et al. ”Fast-vqa: Efficient end-to-end video quality as- sessment with fragment sampling.” European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022. JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 14 Zehao Zhu received the B.E. degree in electronic in- formation engineering from Jilin University in 2018 and th...

    work page 2022

  69. [73]

    His research interests include image quality assessment, perceptual signal processing and mobile video processing

    He is currently a Post-Doctoral Fellow with Shanghai Jiao Tong University. His research interests include image quality assessment, perceptual signal processing and mobile video processing. Jun Jia received the B.S. degree in computer science and technology from Hunan University, Changsha, China, in 2018. He is currently pursuing the Ph.D. degree in elect...

    work page 2018