Research map / Video / Video segmentation and tracking
FAST-VQA: Efficient End-to-End Video Quality Assessment with Fragment Sampling
Haoning Wu, Chaofeng Chen, Jingwen Hou, Liang Liao, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use fragments instead of bilinear resizing (ablation) | FAST-VQA · LSVQ-1080p | SRCC: 0.752 -> 0.779 | Improved |
| use fragments instead of random cropping (ablation) | FAST-VQA · LSVQ-1080p | SRCC: 0.643 -> 0.779 | Improved |
| test with 6 crops instead of a single random crop (ablation) | random cropping · LSVQ-1080p | SRCC: 0.643 -> 0.734 | Improved |
| use uniform grid partition instead of random mini-patches (ablation) | FAST-VQA · LSVQ-1080p | SRCC: 0.754 -> 0.779 | Improved |
| keep spatial order of mini-patches instead of shuffling (ablation) | FAST-VQA · LSVQ-1080p | SRCC: 0.761 -> 0.779 | Improved |
| add temporal alignment of fragments (ablation) | FAST-VQA · LSVQ-1080p | SRCC: 0.736 -> 0.779 | Improved |
| add gated relative position biases (GRPB) (ablation) | FANet · LSVQ-1080p | SRCC: 0.769 -> 0.779 | Improved |
| use IP-NLR head instead of linear regression (ablation) | FANet · LSVQ-1080p | SRCC: 0.768 -> 0.779 | Improved |
| use IP-NLR head instead of pre-pooling non-linear regression (ablation) | FANet · LSVQ-1080p | SRCC: 0.771 -> 0.779 | Improved |
| pretrain on LSVQ with FAST-VQA before finetuning (ablation) | FAST-VQA · LIVE-VQC | SRCC: 0.765 -> 0.849 | Improved |
| pretrain on LSVQ with FAST-VQA before finetuning (ablation) | FAST-VQA · KoNViD-1k | SRCC: 0.842 -> 0.891 | Improved |
| pretrain on LSVQ with FAST-VQA before finetuning (ablation) | FAST-VQA · CVD2014 | SRCC: 0.871 -> 0.891 | Improved |
Later papers that compared with this method
12 later accepted papers report FAST-VQA as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.
- Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment (AAAI 2026 · better on 5 of 6 shared results)
- Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos (CVPR 2026 · better on 1 of 1 shared result)
- DREAM: A Benchmark Study for Deepfake PhotoRealism AssessMent (TPAMI 2026 · better on 1 of 1 shared result)
- KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception (CVPR 2025 · better on 6 of 6 shared results)
- VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations (NeurIPS 2025 · better on 3 of 4 shared results)
- FineVQ: Fine-Grained User Generated Content Video Quality Assessment (CVPR 2025 · better on 2 of 2 shared results)
- MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment (ICCV 2025 · better on 1 of 1 shared result)
- KVQ: Kwai Video Quality Assessment for Short-form Videos (CVPR 2024 · better on 5 of 5 shared results)
4 more not listed.
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild (CVPR 2024 · similarity 0.91)
- Modular Blind Video Quality Assessment (CVPR 2024 · similarity 0.88)
- Scaling and Masking: A New Paradigm of Data Sampling for Image and Video Quality Assessment (AAAI 2024 · similarity 0.88)
- KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception (CVPR 2025 · similarity 0.88)
- AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM (CVPR 2025 · similarity 0.86)
- LAVIB: A Large-scale Video Interpolation Benchmark (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
