Task leaderboard
Last updated
Task leaderboard
2 reported results · Leaderboard page · Dataset details
| Rank | Method & evaluation | Accuracy↑ Higher is better |
|---|---|---|
| 1 | A cross-subject stress recognition method integr A cross-subject stress recognition method integrating bidirectional cross-modal multi-path fusion and adaptive adversarial learning (WESAD; in Chinese) Evaluation detailscross-subject (scheme and number of classes not stated in English abstract); multimodal fusion + subject-adversarial training Weights: not released Reported as of: 2026-10-27 | 0.9158 |
| 2 | BLPEvaluation detailschest ECG 700 Hz → 61 HRV features, 60-s windows / 0.25-s shift; subject-independent 5-fold CV; UAR 0.808, MCC 0.614 in body Label set: binary (baseline+amusement vs stress) Weights: not released Reported as of: 2026-10-19 | 0.823 |
Rows are ranked only within this task × dataset × metric. Protocols can differ; read each method’s evaluation details before comparing.
New entry: A cross-subject stress recognition method…, 0.9158
Stress detection (acute / prolonged / affect): WESAD: accuracy
SOTA star awarded to SimCLR, 0.77
From the hub's dated sync history: new results as they are added, and SOTA stars as they are awarded or move.
Rankings apply within each dataset and metric. Open evaluation details for differences in protocols.
| Rank | Method & evaluation | Accuracy↑ Higher is better |
|---|---|---|
| 1 | BLPEvaluation details185 hospital workers; daily HRV from 5-min RR segments derived from HR, 13 functionals → RFE 100 features + 17 attributes; subject-independent 5-fold CV; UAR 0.630, MCC 0.261 in body Label set: binary daily stress (label construction per paper ref [7]) Weights: not released Reported as of: 2026-10-19 | 0.631 |
| Rank | Method & evaluation | Accuracy↑ Higher is better |
|---|---|---|
| 1 | A cross-subject stress recognition method integr A cross-subject stress recognition method integrating bidirectional cross-modal multi-path fusion and adaptive adversarial learning (WESAD; in Chinese) Evaluation detailscross-subject (scheme and number of classes not stated in English abstract); multimodal fusion + subject-adversarial training Weights: not released Reported as of: 2026-10-27 | 0.9158 |
| 2 | BLPEvaluation detailschest ECG 700 Hz → 61 HRV features, 60-s windows / 0.25-s shift; subject-independent 5-fold CV; UAR 0.808, MCC 0.614 in body Label set: binary (baseline+amusement vs stress) Weights: not released Reported as of: 2026-10-19 | 0.823 |