mlsanityData to 7 Oct 2026

FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling

arXiv 2207.02595 ↗First posted 6 Jul 2022cs.CV cs.MMcited by 179

Not on the map. Why?

Abstract (arXiv)

Current deep video quality assessment (VQA) methods are usually with high computational costs when evaluating high-resolution videos. This cost hinders them from learning better video-quality-related representations via end-to-end training. Existing approaches typically consider naive sampling to reduce the computational cost, such as resizing and cropping. However, they obviously corrupt quality-related information in videos and are thus not optimal for learning good representations for VQA. Therefore, there is an eager need to design a new quality-retained sampling scheme for VQA. In this paper, we propose Grid Mini-patch Sampling (GMS), which allows consideration of local quality by sampling patches at their raw resolution and covers global quality with contextual relations via mini-patches sampled in uniform grids. These mini-patches are spliced and aligned temporally, named as fragments. We further build the Fragment Attention Network (FANet) specially designed to accommodate fragments as inputs. Consisting of fragments and FANet, the proposed FrAgment Sample Transformer for VQA (FAST-VQA) enables efficient end-to-end deep VQA and learns effective video-quality-related representations. It improves state-of-the-art accuracy by around 10% while reducing 99.5% FLOPs on 1080P high-resolution videos. The newly learned video-quality-related representations can also be transferred into smaller VQA datasets, boosting performance in these scenarios. Extensive experiments show that FAST-VQA has good performance on inputs of various resolutions while retaining high efficiency. We publish our code at https://github.com/timothyhtimothy/FAST-VQA.

Key facts. Cited by 179 papers in the map (data through 7 Oct 2026). Builds on 26 of its 46 references that are in the map. First posted on arXiv 6 Jul 2022.

Builds on

26 of 46 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  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. 2021ViViT: A Video Vision Transformercited by 1,610
  8. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  9. 2021Video Swin Transformercited by 1,090
  10. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  11. 2021Multiscale Vision Transformerscited by 896
  12. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
14 more
  1. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
  2. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 301
  3. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 221
  4. 2017Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognitioncited by 178
  5. 2019Quality Assessment of In-the-Wild Videoscited by 164
  6. 2020Patch-VQ: 'Patching Up' the Video Quality Problemcited by 147
  7. 2020UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Contentcited by 140
  8. 2018Large-Scale Study of Perceptual Video Qualitycited by 127
  9. 2021RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Contentcited by 100
  10. 2021Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perceptioncited by 97
  11. 2020Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Trainingcited by 72
  12. 2020Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessmentcited by 50
  13. 2022DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessmentcited by 41
  14. 2020Subjective Quality Assessment for YouTube UGC Datasetcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 29; 2024: 55; 2025: 56; 2026: 34.

179 papers.

Sort:

By area:

  1. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  2. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 489
  3. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 314
  4. 2023Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Visioncited by 247
  5. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 218
  6. 2024VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generationcited by 190
  7. 2023Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Modelscited by 152
  8. 2024Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Contentcited by 132
  9. 2024Towards Open-ended Visual Quality Comparisoncited by 85
  10. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  11. 2024Fr'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videoscited by 54
  12. 2022Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessmentcited by 50
38 more
  1. 2024Towards A Better Metric for Text-to-Video Generationcited by 50
  2. 2023MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videoscited by 46
  3. 2023SWinGS: Sliding Windows for Dynamic 3D Gaussian Splattingcited by 46
  4. 2023Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approachcited by 45
  5. 2024Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessmentcited by 39
  6. 2024Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMscited by 39
  7. 2023Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Modelscited by 38
  8. 2024KVQ: Kwai Video Quality Assessment for Short-form Videoscited by 38
  9. 2024GAIA: Rethinking Action Quality Assessment for AI-Generated Videoscited by 30
  10. 2025PAI-Bench: A Comprehensive Benchmark For Physical AIcited by 30
  11. 2024NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Resultscited by 29
  12. 2024LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Modelscited by 28
  13. 2024FineVQ: Fine-Grained User Generated Content Video Quality Assessmentcited by 28
  14. 2024Quality Assessment in the Era of Large Models: A Surveycited by 26
  15. 2025VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learningcited by 26
  16. 2022Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessmentcited by 25
  17. 2024AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMMcited by 24
  18. 2023Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterioncited by 23
  19. 2024Modular Blind Video Quality Assessmentcited by 23
  20. 2023Exploring the Naturalness of AI-Generated Imagescited by 22
  21. 2023Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Modelscited by 22
  22. 2023Zoom-VQA: Patches, Frames and Clips Integration for Video Quality Assessmentcited by 21
  23. 2023GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessmentcited by 20
  24. 2023Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessmentcited by 20
  25. 2024NTIRE 2024 Quality Assessment of AI-Generated Content Challengecited by 20
  26. 2024Enhancing Blind Video Quality Assessment with Rich Quality-aware Featurescited by 19
  27. 2024PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wildcited by 17
  28. 2023Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video Quality Assessmentcited by 16
  29. 2023StableVQA: A Deep No-Reference Quality Assessment Model for Video Stabilitycited by 15
  30. 2024VQA2: Visual Question Answering for Video Quality Assessmentcited by 15
  31. 2024Video Quality Assessment: A Comprehensive Surveycited by 15
  32. 2025NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Resultscited by 14
  33. 2024Scaling and Masking: A New Paradigm of Data Sampling for Image and Video Quality Assessmentcited by 13
  34. 2024Exploring AIGC Video Quality: A Focus on Visual Harmony, Video-Text Consistency and Domain Distribution Gapcited by 13
  35. 2024Quality Assessment for AI Generated Images with Instruction Tuningcited by 13
  36. 2024Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Modelcited by 13
  37. 2025FVQ: A Large-Scale Dataset and an LMM-based Method for Face Video Quality Assessmentcited by 13
  38. 2023Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancementcited by 12

50 most cited of 179 All 179 (JSON)