AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

SATTC: Structure-Aware Label-Free Test-Time Calibration for Cross-Subject EEG-to-Image Retrieval

Qunjie Huang, Weina Zhu

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 2 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 subject-adaptive whitening (SAW) to EEG embeddings (ablation)Standardized baseline · THINGS-EEG 200-way LOSOTop-5 / Top-1 accuracy (%): Top-5 30.5 -> 36.4; Top-1 9.2 -> 13.7Improved
add candidate whitening on top of SAW (ablation)+SAW · THINGS-EEG 200-way LOSOTop-5 / Top-1 accuracy (%): Top-5 36.4 -> 36.8; Top-1 13.7 -> 13.5No clear effect
add fixed-k CSLS (k=12) on SAW+CW (ablation)+SAW+CW · THINGS-EEG 200-way LOSOTop-5 accuracy (%): 36.8 -> 38.1Improved
replace fixed-k CSLS with adaptive CSLS (ablation)+SAW+CW+CSLS · THINGS-EEG 200-way LOSOTop-5 / Top-1 accuracy (%): Top-5 38.1 -> 38.8; Top-1 14.1 -> 13.9Mixed
add structural expert with PoE fusion on adaptive CSLS (ablation)+SAW+CW+Ada-CSLS · THINGS-EEG 200-way LOSOTop-1 accuracy (%): 13.9 -> 14.8Improved
add structural expert with PoE fusion on adaptive CSLS (ablation)+SAW+CW+Ada-CSLS · THINGS-EEG 200-way LOSOTop-5 accuracy (%): 38.8 -> 38.4No clear effect
use standardized inference (cosine, l2, candidate whitening) instead of original ATM dot-productATM · THINGS-EEG 200-way LOSOTop-5 / Top-1 accuracy (%): Top-5 20.0 -> 30.5; Top-1 5.5 -> 9.2Improved
apply SATTC calibration head to EEGNetV4EEGNetV4 · THINGS-EEG 200-way LOSOTop-5 / Top-1 accuracy (%): Top-5 20.5 -> 34.8; Top-1 5.4 -> 10.8Improved
apply SATTC calibration head to EEGConformerEEGConformer · THINGS-EEG 200-way LOSOTop-5 / Top-1 accuracy (%): Top-5 11.6 -> 23.2; Top-1 2.5 -> 6.9Improved
apply SATTC calibration head to ShallowFBCSPNetShallowFBCSPNet · THINGS-EEG 200-way LOSOTop-5 / Top-1 accuracy (%): Top-5 14.6 -> 30.8; Top-1 3.5 -> 11.1Improved
use adaptive CSLS instead of fixed-k CSLS for hubness (ablation)CSLS · THINGS-EEG class popularityhubness (class-occurrence curve)Improved
use unlabeled calibration window of N=50 instead of N=200 (ablation)SAW+CSLS · THINGS-EEG N-shotfraction of upper bound: 94.8% of the N = 200 upper boundNo clear effect

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