AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking

Kanglong Fan, Tianhe Wu, Wen Wen, Jianzhao Liu, le yang, Yabin ZHANG, Yiting Liao, Junlin Li, Li Zhang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 1 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
add ME-IQA test-time memory re-rankingVisualQuality-R1 · IQA WAVG over 7 benchmarks (KonIQ-trained)PLCC: 0.698 -> 0.726Improved
add ME-IQA test-time memory re-rankingEvoQuality · IQA WAVG over 7 benchmarks (KonIQ-trained)SRCC: 0.716 -> 0.751Improved
add ME-IQA test-time memory re-rankingGPT-5 · IQA WAVG over 7 benchmarks (KonIQ-trained)PLCC: 0.676 -> 0.706Improved
replace 64-sample majority voting with ME-IQA@32VisualQuality-R1 · IQA WAVG over 7 benchmarks (KonIQ-trained)PLCC: 0.710 -> 0.726Improved
increase neighborhood size K from 0 to 32 (ablation)ME-IQA · IQA WAVG over 7 benchmarks (KonIQ-trained)PLCC: 0.698 -> 0.726Improved
increase K from 32 to 256 (ablation)ME-IQA · IQA WAVG over 7 benchmarks (KonIQ-trained)PLCC: 0.726 -> 0.735No clear effect
lengthen direct reasoning to L=500 instead of ME-IQA (ablation)Direct scoring · IQA WAVG over 7 benchmarks (KonIQ-trained)PLCC: 0.698 -> 0.689Hurt
use reasoning embeddings instead of random retrieval (ablation)ME-IQA · IQA WAVG over 7 benchmarks (KonIQ-trained)PLCC: 0.703 -> 0.726Improved
use reasoning embeddings instead of image embeddings (ablation)ME-IQA · IQA WAVG over 7 benchmarks (KonIQ-trained)PLCC: 0.706 -> 0.726Improved
add consistency reward in RL finetuning (reasoning embeddings*) (ablation)ME-IQA · IQA WAVG over 7 benchmarks (KonIQ-trained)PLCC: 0.726 -> 0.737Improved
use pairwise Thurstone re-ranking instead of kernel re-scoring (ablation)ME-IQA · KADIDPLCC: 0.707 -> 0.741Improved
add quadratic prior lambda=1e-2 to Thurstone fusion (ablation)ME-IQA · KADIDPLCC: 0.724 -> 0.741Improved

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