Loading
Life sciences · Preprint
arXiv · August 19, 2026
Early or partial results. Treat as a signal, not a conclusion.
This is an unreviewed preprint describing SCORE, a novel computational method for aligning EEG signals across subjects to improve cross-subject image retrieval without target-subject labeling. The work reports improvements in retrieval accuracy on two public benchmarks but does not establish clinical utility, neuroscientific insight, or real-world applicability beyond technical performance metrics.
Algorithm development and evaluation on public benchmark datasets. Subjects from two public EEG-image datasets: THINGS-EEG2 and Alljoined-1.6M. Exact number of subjects, inclusion/exclusion criteria, and demographic details not reported.. Intervention: Subject Coordinate Recovery (SCORE) framework for cross-subject EEG-to-image retrieval without target-subject labels. Compared with: Unadapted baseline and other unspecified strongest baselines.
SCORE achieves 53.23% Top-1 and 83.55% Top-5 accuracy on THINGS-EEG2 benchmark SCORE achieves 12.01% Top-1 and 32.16% Top-5 accuracy on Alljoined-1.6M benchmark SCORE outperforms strongest baselines by 17.45 and 15.70 percentage points (Top-1/Top-5) on THINGS-EEG2
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
Not applicable. This is a technical methods paper without clinical endpoints, patient outcomes, or validation in any clinical context. Relevance to neural communication or brain–computer interface deployment remains unestablished.
This is a first-report computational methods paper on a novel algorithm for cross-subject EEG-to-image retrieval, lacking clinical validation, peer review, and any outcome measures relevant to clinical practice or neuroscience understanding.
As stated by the source record.
Quoted from the source exactly as published.
Not applicable. This is a technical methods paper without clinical endpoints, patient outcomes, or validation in any clinical context. Relevance to neural communication or brain–computer interface deployment remains unestablished.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Accurate visual decoding can reveal how the brain represents visual information and recover perceived content from neural signals such as electroencephalography (EEG), with potential for neural communication. However, current EEG-to-image retrieval methods perform far below their within-subject counterparts for new users without labeled calibration, limiting real-world deployment. To understand this gap, we analyze EEG features across subjects and find that different subjects preserve similar relationships among concepts but express them along different coordinate directions. We therefore propose Subject Coordinate Recovery (SCORE), a target label-free framework combining recovery-aware source training with coordinate alignment at deployment. During training, SCORE aligns source subject EEG with a common image space and simulates unseen-subject recovery through source-only episodes. At deployment, with both encoders frozen, SCORE selects reliable EEG-image landmarks through hubness-corrected matching and estimates an orthogonal transformation to recover target EEG coordinates without source data or target labels. In 200-way retrieval on two public benchmarks, SCORE outperforms the unadapted baseline for every target subject and achieves the best overall accuracy. It reaches 53.23%/83.55% and 12.01%/32.16% Top-1/Top-5 on THINGS-EEG2 and Alljoined-1.6M, respectively, surpassing the strongest baselines by 17.45/15.70 and 3.08/4.62 percentage points. Without target labels or encoder updates, SCORE brings brain-based visual decoding closer to robust, practical, low-latency deployment across users.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.