Research map / Video / Video-language understanding
MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment
Yachun Mi, Yu Li, Weicheng Meng, Chaofeng Chen, Chen Hui, Shaohui Liu
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 |
|---|---|---|---|
| replace Fragments sampling with USDS (ablation) | MVQA · LSVQ test | SROCC: 0.864 -> 0.882 | Improved |
| use USDS instead of resize sampling (ablation) | MVQA · LSVQ test | SROCC: 0.847 -> 0.882 | Improved |
| use USDS instead of crop sampling (ablation) | MVQA · LSVQ test | SROCC: 0.798 -> 0.882 | Improved |
| use USDS instead of Fragments in Video Swin Transformer (ablation) | Video Swin Transformer · LSVQ test | SROCC: 0.872 -> 0.877 | Improved |
| increase video resolution under USDS versus Fragments/MRET (ablation) | MVQA · different video resolutions | SROCC/PLCC | Improved |
| use Mamba-based MVQA-tiny instead of FasterVQA | MVQA-tiny · Efficiency | FLOPs: 70 -> 34 | Improved |
| use MVQA-tiny instead of FasterVQA on accuracy | MVQA-tiny · LSVQ test | SROCC: 0.873 -> 0.882 | Improved |
| scale from MVQA-tiny to MVQA-middle | MVQA · LIVE-VQC cross-dataset | SROCC: 0.828 -> 0.852 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FAST-VQA — FAST-VQA: Efficient End-to-End Video Quality Assessment with Fragment Sampling (ECCV 2022) · better on 1 of 1 shared result
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 0.89)
- Scaling and Masking: A New Paradigm of Data Sampling for Image and Video Quality Assessment (AAAI 2024 · similarity 0.87)
- AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM (CVPR 2025 · similarity 0.86)
- Modular Blind Video Quality Assessment (CVPR 2024 · similarity 0.86)
- KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception (CVPR 2025 · similarity 0.85)
- QMamba: On First Exploration of Vision Mamba for Image Quality Assessment (ICML 2025 · similarity 0.85)
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.
