M3ED
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Emotion Recognition | M3ED (test) | Weighted F152.28 | 35 | |
| Emotion Recognition | M3ED (val) | Weighted F158.7 | 35 | |
| Localization | M3ED (test) | Translation Error (cm)6.85 | 20 | |
| Event-based Stereo Matching | M3ED Indoor | 1 Pixel Error (1PE)38.93 | 12 | |
| Event-based Stereo Matching | M3ED (Night) | 1PE46.9 | 12 | |
| Event-based Stereo Matching | M3ED (Day) | 1PE26.38 | 12 | |
| Visual-Inertial Odometry | M3ED | Accuracy (Hard Sequence)57 | 11 | |
| Ego-motion Estimation | M3ED | Translation Error (m)0.22 | 6 | |
| Optical Flow | M3ED | Flow Error (px)1.59 | 6 | |
| Depth Estimation | M3ED | Depth (m)9.75 | 6 | |
| Egomotion estimation | M3ED (falcon_indoor_flight_1) | Median Angular Error0.1242 | 6 | |
| Event-to-Event Matching | M3ED | AUC@5°52.99 | 6 | |
| Semantic Segmentation | M3ED Quadruped | mIoU69.27 | 6 | |
| Semantic Segmentation | M3ED (Drone) | mIoU64.57 | 6 | |
| Event-to-Image Matching | M3ED Dataset | AUC @ 5°54.97 | 5 | |
| Speech Emotion Recognition | M3ED | Macro F132.1 | 5 | |
| Speech Emotion Recognition | M3ED Chinese (Zh) | Weighted Accuracy (WA)49.15 | 5 | |
| Semantic Segmentation | M3ED Urban Day (test) | mIoU67.28 | 4 | |
| Disparity Estimation | M3ED (test) | MAE0.813 | 3 |
Showing 19 of 19 rows