AI Paper Atlas

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

ECCV 2022 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 299 citations (OpenAlex)

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 changedWhereMeasuredEffect
use fragments instead of bilinear resizing (ablation)FAST-VQA · LSVQ-1080pSRCC: 0.752 -> 0.779Improved
use fragments instead of random cropping (ablation)FAST-VQA · LSVQ-1080pSRCC: 0.643 -> 0.779Improved
test with 6 crops instead of a single random crop (ablation)random cropping · LSVQ-1080pSRCC: 0.643 -> 0.734Improved
use uniform grid partition instead of random mini-patches (ablation)FAST-VQA · LSVQ-1080pSRCC: 0.754 -> 0.779Improved
keep spatial order of mini-patches instead of shuffling (ablation)FAST-VQA · LSVQ-1080pSRCC: 0.761 -> 0.779Improved
add temporal alignment of fragments (ablation)FAST-VQA · LSVQ-1080pSRCC: 0.736 -> 0.779Improved
add gated relative position biases (GRPB) (ablation)FANet · LSVQ-1080pSRCC: 0.769 -> 0.779Improved
use IP-NLR head instead of linear regression (ablation)FANet · LSVQ-1080pSRCC: 0.768 -> 0.779Improved
use IP-NLR head instead of pre-pooling non-linear regression (ablation)FANet · LSVQ-1080pSRCC: 0.771 -> 0.779Improved
pretrain on LSVQ with FAST-VQA before finetuning (ablation)FAST-VQA · LIVE-VQCSRCC: 0.765 -> 0.849Improved
pretrain on LSVQ with FAST-VQA before finetuning (ablation)FAST-VQA · KoNViD-1kSRCC: 0.842 -> 0.891Improved
pretrain on LSVQ with FAST-VQA before finetuning (ablation)FAST-VQA · CVD2014SRCC: 0.871 -> 0.891Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy