Task leaderboard
Last updated
Task leaderboard
1 reported result · Leaderboard page · Dataset details
| Rank | Method & evaluation | Accuracy↑ Higher is better |
|---|---|---|
| 1 | CEAP-360VR CEAP-360VR: A Continuous Physiological and Behavioral Emotion Annotation Dataset for 360° VR Videos Evaluation detailsRandom Forest, 2 s segments, physiological features only (E4 EDA, IBI, HR, SKT, BVP), subject-independent LOSO (Table IV); weighted F1 0.6126 Label set: binary low/high valence (continuous annotation) Reported as of: 2026-10-30 | 0.6569 |
One reported result is available; this is not a multi-method comparison. Rows are ranked only within this task × dataset × metric. Protocols can differ; read each method’s evaluation details before comparing.
Rankings apply within each dataset and metric. Open evaluation details for differences in protocols.
| Rank | Method & evaluation | Accuracy↑ Higher is better |
|---|---|---|
| 1 | CEAP-360VR CEAP-360VR: A Continuous Physiological and Behavioral Emotion Annotation Dataset for 360° VR Videos Evaluation detailsRandom Forest, 2 s segments, physiological features only (E4 EDA, IBI, HR, SKT, BVP), subject-independent LOSO (Table IV); weighted F1 0.6126 Label set: binary low/high valence (continuous annotation) Reported as of: 2026-10-30 | 0.6569 |
| Rank | Method & evaluation | Macro-averaged F1↑ Higher is better |
|---|---|---|
| 1 | Pseudo-Label Augmentation for Affect Sensing in… Pseudo-Label Augmentation for Affect Sensing in Small Collaborative Groups Evaluation detailsKnown-team, test task T3; RBF-SVM on 49 physiology + eye-tracking window features (15 s); GP pseudo-labels + personality cosine weighting (A2); Table 7 Label set: 3-class SAM valence (train-fitted midpoint tertiles) Reported as of: 2026-10-30 | 0.608 |
| Rank | Method & evaluation | Macro-averaged F1↑ Higher is better |
|---|---|---|
| 1 | Introducing WARM-VR Introducing WARM-VR: Benchmark Dataset for Multimodal Wearable Affect Recognition in Virtual Reality Evaluation detailsE4 wrist BVP only, 60 s windows, CNN (tie CNN-Bi-GRU), subject-independent 5-fold CV; AUC 0.69 (Table 2) Label set: binary low/high SAM valence Reported as of: 2026-10-30 | 0.63 |
| Rank | Method & evaluation | Macro-averaged F1↑ Higher is better |
|---|---|---|
| 1 | Introducing WESAD, a Multimodal Dataset for… Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection Evaluation detailsWrist physio (E4 BVP+EDA+TEMP) features, 60 s windows, 0.25 s shift, Random Forest, LOSO (15 subjects); accuracy 76.17% Label set: 3-class baseline / stress / amusement Reported as of: 2026-10-30 | 0.6633 |