mlsanityData to 7 Oct 2026

Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception

arXiv 2108.08505 ↗First posted 19 Aug 2021eess.IV cs.CVcited by 97

Not on the map. Why?

Abstract (arXiv)

Perceptual quality assessment of the videos acquired in the wilds is of vital importance for quality assurance of video services. The inaccessibility of reference videos with pristine quality and the complexity of authentic distortions pose great challenges for this kind of blind video quality assessment (BVQA) task. Although model-based transfer learning is an effective and efficient paradigm for the BVQA task, it remains to be a challenge to explore what and how to bridge the domain shifts for better video representation. In this work, we propose to transfer knowledge from image quality assessment (IQA) databases with authentic distortions and large-scale action recognition with rich motion patterns. We rely on both groups of data to learn the feature extractor. We train the proposed model on the target VQA databases using a mixed list-wise ranking loss function. Extensive experiments on six databases demonstrate that our method performs very competitively under both individual database and mixed database training settings. We also verify the rationality of each component of the proposed method and explore a simple manner for further improvement.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). Builds on 31 of its 87 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

31 of 87 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2017The Kinetics Human Action Video Datasetcited by 1,894
  7. 2018SlowFast Networks for Video Recognitioncited by 1,862
  8. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  9. 2021Domain Generalization: A Surveycited by 760
  10. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
  11. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 301
  12. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 221
19 more
  1. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 208
  2. 2020Fast Differentiable Sorting and Rankingcited by 196
  3. 2017Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognitioncited by 178
  4. 2019Quality Assessment of In-the-Wild Videoscited by 164
  5. 2020Patch-VQ: 'Patching Up' the Video Quality Problemcited by 147
  6. 2020UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Contentcited by 140
  7. 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
  8. 2018Large-Scale Study of Perceptual Video Qualitycited by 127
  9. 2019YouTube UGC Dataset for Video Compression Researchcited by 124
  10. 2021RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Contentcited by 100
  11. 2020MotionSqueeze: Neural Motion Feature Learning for Video Understandingcited by 72
  12. 2020Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Trainingcited by 72
  13. 2016Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approachcited by 71
  14. 2021Continual Learning for Blind Image Quality Assessmentcited by 36
  15. 2020A Comparative Evaluation of Temporal Pooling Methods for Blind Video Quality Assessmentcited by 22
  16. 2021Quantifying Visual Image Quality: A Bayesian Viewcited by 20
  17. 2021Task-Specific Normalization for Continual Learning of Blind Image Quality Modelscited by 18
  18. 2020Perceptual Video Quality Prediction Emphasizing Chroma Distortionscited by 10
  19. 2021Regression or Classification? New Methods to Evaluate No-Reference Picture and Video Quality Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 12; 2023: 17; 2024: 35; 2025: 21; 2026: 12.

97 papers.

Sort:

By area:

  1. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 489
  2. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 314
  3. 2022FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Samplingcited by 179
  4. 2022A Deep Learning based No-reference Quality Assessment Model for UGC Videoscited by 128
  5. 2022Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessmentcited by 50
  6. 2024Towards A Better Metric for Text-to-Video Generationcited by 50
  7. 2023MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videoscited by 46
  8. 2023Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approachcited by 45
  9. 2022DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessmentcited by 41
  10. 2024Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMscited by 39
  11. 2023Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Modelscited by 38
  12. 2024KVQ: Kwai Video Quality Assessment for Short-form Videoscited by 38
38 more
  1. 2024GAIA: Rethinking Action Quality Assessment for AI-Generated Videoscited by 30
  2. 2024NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Resultscited by 29
  3. 2024LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Modelscited by 28
  4. 2024AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMMcited by 24
  5. 2023Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterioncited by 23
  6. 2024Modular Blind Video Quality Assessmentcited by 23
  7. 2022Going the Extra Mile in Face Image Quality Assessment: A Novel Database and Modelcited by 22
  8. 2023Exploring the Naturalness of AI-Generated Imagescited by 22
  9. 2023Zoom-VQA: Patches, Frames and Clips Integration for Video Quality Assessmentcited by 21
  10. 2023Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessmentcited by 20
  11. 2022CONVIQT: Contrastive Video Quality Estimatorcited by 19
  12. 2024Enhancing Blind Video Quality Assessment with Rich Quality-aware Featurescited by 19
  13. 2023Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessmentcited by 18
  14. 2024PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wildcited by 17
  15. 2023Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video Quality Assessmentcited by 16
  16. 2023StableVQA: A Deep No-Reference Quality Assessment Model for Video Stabilitycited by 15
  17. 2024VQA2: Visual Question Answering for Video Quality Assessmentcited by 15
  18. 2024Video Quality Assessment: A Comprehensive Surveycited by 15
  19. 2024Scaling and Masking: A New Paradigm of Data Sampling for Image and Video Quality Assessmentcited by 13
  20. 2024Exploring AIGC Video Quality: A Focus on Visual Harmony, Video-Text Consistency and Domain Distribution Gapcited by 13
  21. 2023Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancementcited by 12
  22. 2023Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attackscited by 12
  23. 2023CLiF-VQA: Enhancing Video Quality Assessment by Incorporating High-Level Semantic Information related to Human Feelingscited by 11
  24. 2024CLIPVQA:Video Quality Assessment via CLIPcited by 11
  25. 2025KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perceptioncited by 11
  26. 2022FAVER: Blind Quality Prediction of Variable Frame Rate Videoscited by 10
  27. 2025LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretationcited by 10
  28. 2024Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metriccited by 9
  29. 2025VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learningcited by 9
  30. 2024THQA: A Perceptual Quality Assessment Database for Talking Headscited by 8
  31. 2024QPT V2: Masked Image Modeling Advances Visual Scoringcited by 8
  32. 2023Knowledge Guided Semi-Supervised Learning for Quality Assessment of User Generated Videoscited by 7
  33. 2022REQA: Coarse-to-fine Assessment of Image Quality to Alleviate the Range Effectcited by 6
  34. 2024SHE-Net: Syntax-Hierarchy-Enhanced Text-Video Retrievalcited by 6
  35. 2024Light-VQA+: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidancecited by 6
  36. 2025T2VEval: Benchmark Dataset and Objective Evaluation Method for T2V-generated Videoscited by 6
  37. 2022Boosting Point-BERT by Multi-choice Tokenscited by 5
  38. 2022HVS Revisited: A Comprehensive Video Quality Assessment Frameworkcited by 5

50 most cited of 97 All 97 (JSON)