mlsanityData to 7 Oct 2026

Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives

arXiv 2211.04894 ↗First posted 9 Nov 2022cs.CV cs.LG cs.MMcited by 314

Not on the map. Why?

Cited by 77 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The rapid increase in user-generated-content (UGC) videos calls for the development of effective video quality assessment (VQA) algorithms. However, the objective of the UGC-VQA problem is still ambiguous and can be viewed from two perspectives: the technical perspective, measuring the perception of distortions; and the aesthetic perspective, which relates to preference and recommendation on contents. To understand how these two perspectives affect overall subjective opinions in UGC-VQA, we conduct a large-scale subjective study to collect human quality opinions on overall quality of videos as well as perceptions from aesthetic and technical perspectives. The collected Disentangled Video Quality Database (DIVIDE-3k) confirms that human quality opinions on UGC videos are universally and inevitably affected by both aesthetic and technical perspectives. In light of this, we propose the Disentangled Objective Video Quality Evaluator (DOVER) to learn the quality of UGC videos based on the two perspectives. The DOVER proves state-of-the-art performance in UGC-VQA under very high efficiency. With perspective opinions in DIVIDE-3k, we further propose DOVER++, the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective. Code at https://github.com/VQAssessment/DOVER.

Key facts. Cited by 314 papers in the map (data through 7 Oct 2026). Builds on 40 of its 78 references that are in the map. First posted on arXiv 9 Nov 2022.

Builds on

40 of 78 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2022A ConvNet for the 2020scited by 3,545
  4. 2017The Kinetics Human Action Video Datasetcited by 1,894
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  6. 2021Video Swin Transformercited by 1,090
  7. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  8. 2017NIMA: Neural Image Assessmentcited by 387
  9. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
  10. 2020BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyondcited by 303
  11. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 301
  12. 2017Temporal Segment Networks for Action Recognition in Videoscited by 279
28 more
  1. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 221
  2. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 208
  3. 2022FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Samplingcited by 179
  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. 2022A Deep Learning based No-reference Quality Assessment Model for UGC Videoscited by 128
  9. 2018Large-Scale Study of Perceptual Video Qualitycited by 127
  10. 2019YouTube UGC Dataset for Video Compression Researchcited by 124
  11. 2016Photo Aesthetics Ranking Network with Attributes and Content Adaptationcited by 122
  12. 2021RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Contentcited by 100
  13. 2021Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perceptioncited by 97
  14. 2020Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Trainingcited by 72
  15. 2016Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approachcited by 71
  16. 2022Personalized Image Aesthetics Assessment with Rich Attributescited by 56
  17. 2020Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessmentcited by 54
  18. 2019Effective Aesthetics Prediction with Multi-level Spatially Pooled Featurescited by 52
  19. 2020Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessmentcited by 50
  20. 2022Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessmentcited by 50
  21. 2022DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessmentcited by 41
  22. 2020ST-GREED: Space-Time Generalized Entropic Differences for Frame Rate Dependent Video Quality Predictioncited by 33
  23. 2022Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessmentcited by 25
  24. 2021Image Composition Assessment with Saliency-augmented Multi-pattern Poolingcited by 21
  25. 2022Efficient Video Deblurring Guided by Motion Magnitudecited by 16
  26. 2022Distilling Knowledge from Object Classification to Aesthetics Assessmentcited by 12
  27. 2018A Gated Peripheral-Foveal Convolutional Neural Network for Unified Image Aesthetic Predictioncited by 11
  28. 2020Subjective Quality Assessment for YouTube UGC Datasetcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 15; 2024: 72; 2025: 136; 2026: 91.

314 papers.

Sort:

By area:

  1. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  2. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  3. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 568
  4. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 489
  5. 2023EvalCrafter: Benchmarking and Evaluating Large Video Generation Modelscited by 332
  6. 2024OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generationcited by 332
  7. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 286
  8. 2023Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Visioncited by 247
  9. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 218
  10. 2024VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generationcited by 190
  11. 2025World Simulation with Video Foundation Models for Physical AIcited by 183
  12. 2024SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Accelerationcited by 158
38 more
  1. 2023Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Modelscited by 152
  2. 2025HunyuanVideo 1.5 Technical Reportcited by 148
  3. 2024Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Contentcited by 132
  4. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
  5. 2024ID-Animator: Zero-Shot Identity-Preserving Human Video Generationcited by 122
  6. 2024SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantizationcited by 113
  7. 2025SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inferencecited by 113
  8. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationcited by 110
  9. 2025Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Controlcited by 95
  10. 2025SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformercited by 91
  11. 2024Towards Open-ended Visual Quality Comparisoncited by 85
  12. 2024OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generationcited by 77
  13. 2025Wan-Animate: Unified Character Animation and Replacement with Holistic Replicationcited by 76
  14. 2025OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generationcited by 73
  15. 2024Allegro: Open the Black Box of Commercial-Level Video Generation Modelcited by 68
  16. 2024Evaluation of Text-to-Video Generation Models: A Dynamics Perspectivecited by 66
  17. 2024VEnhancer: Generative Space-Time Enhancement for Video Generationcited by 64
  18. 2025SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Trainingcited by 63
  19. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  20. 2025InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Constructioncited by 62
  21. 2025Wan-S2V: Audio-Driven Cinematic Video Generationcited by 60
  22. 2023Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutioncited by 59
  23. 2025UniVerse-1: Unified Audio-Video Generation via Stitching of Expertscited by 58
  24. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
  25. 2023FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Modelscited by 55
  26. 2024Towards A Better Metric for Text-to-Video Generationcited by 50
  27. 2026SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformercited by 50
  28. 2025VMBench: A Benchmark for Perception-Aligned Video Motion Generationcited by 48
  29. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  30. 2024Diffusion Model-Based Video Editing: A Surveycited by 44
  31. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 40
  32. 2024Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessmentcited by 39
  33. 2024Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMscited by 39
  34. 2026MOVA: Towards Scalable and Synchronized Video-Audio Generationcited by 39
  35. 2023Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Modelscited by 38
  36. 2024EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generationcited by 38
  37. 2025VideoScore2: Think before You Score in Generative Video Evaluationcited by 37
  38. 2026Infinite Worlds with Versatile Interactionscited by 37

50 most cited of 314 All 314 (JSON)