Leaderboard
HARENA is a living benchmark for sensor-based human activity recognition, comparing architectures on recognition performance on unseen subjects and measured deployment cost.
Filters
Datasets
All datasets 29/29
Models
All models 19/19
Building Blocks
All building blocks 7/7
Rankings
Compare recognition performance across models, and how often each model lies on a per-dataset Pareto front on the selected device.
| Model | Building Blocks | ||||||
|---|---|---|---|---|---|---|---|
| Affiliations withheld during review | 4.44% ±3.20% | 74.4% | 24.1% | 20.7% | 41.4% | 24.1% | |
| Affiliations withheld during review | 3.98% ±3.32% | 74.0% | 20.7% | 24.1% | 27.6% | 20.7% | |
| Affiliations withheld during review | 3.61% ±3.17% | 73.6% | 34.5% | 31.0% | 20.7% | 34.5% | |
| Affiliations withheld during review | 3.00% ±2.90% | 73.0% | 41.4% | 10.3% | 13.8% | 37.9% | |
| Affiliations withheld during review | 2.55% ±3.40% | 72.5% | 10.3% | 10.3% | 10.3% | 10.3% | |
| Affiliations withheld during review | 2.49% ±2.60% | 72.5% | 69.0% | 55.2% | 89.7% | 69.0% | |
| Affiliations withheld during review | 2.48% ±3.17% | 72.5% | 0.0% | 0.0% | 0.0% | 0.0% | |
| Affiliations withheld during review | 2.23% ±2.99% | 72.2% | 0.0% | 6.9% | 0.0% | 0.0% | |
| Affiliations withheld during review | 0.18% ±3.51% | 70.2% | 0.0% | 0.0% | 0.0% | 0.0% | |
| 100 trees, depth=8 | -0.02% ±0.04% | 70.0% | 86.2% | 86.2% | 37.9% | 86.2% | |
| Affiliations withheld during review | -0.57% ±2.43% | 69.4% | 3.4% | 6.9% | 0.0% | 3.4% | |
| Affiliations withheld during review | -0.59% ±2.70% | 69.4% | 13.8% | 48.3% | 31.0% | 13.8% | |
| Affiliations withheld during review | -1.74% ±3.27% | 68.3% | 0.0% | 0.0% | 0.0% | 0.0% | |
| Affiliations withheld during review | -2.31% ±4.76% | 67.7% | 3.4% | 24.1% | 3.4% | 3.4% | |
| Affiliations withheld during review | -4.76% ±4.38% | 65.2% | 0.0% | 0.0% | 0.0% | 0.0% | |
| Affiliations withheld during review | -6.12% ±3.85% | 63.9% | 0.0% | 0.0% | 0.0% | 0.0% | |
| Affiliations withheld during review | -6.86% ±3.69% | 63.1% | 0.0% | 10.3% | 0.0% | 0.0% | |
| RBF kernel, C=1 | -16.85% ±3.43% | 53.1% | 0.0% | 0.0% | 0.0% | 0.0% | |
| k=5, distance-weighted | -20.42% ±3.37% | 49.6% | 3.4% | 3.4% | 3.4% | 3.4% |