Activity Recognition on WISDM (test)
85.66Top-1 AccuracyPatchTST (Supervised Learning)
Evaluation results
| Method | Links | |
|---|---|---|
| PatchTST (Supervised Learning)# Parameters=0.9M, Evaluation Protocol=Supervised Learning2026.03 | 85.66 | |
| SLIPBase# Parameters=120M, # Time Points=1.7B, Evaluation Protocol=linear-probing2026.03 | 82.36 | |
| SundialBase# Parameters=128M, # Time Points=1032B, Evaluation Protocol=linear-probing2026.03 | 81.25 | |
| ChronosBase# Parameters=200M, # Time Points=12.8B, Evaluation Protocol=linear-probing2026.03 | 80.3 | |
| ChatTS# Parameters=8B, # Time Points=0.23B, Evaluation Protocol=linear-probing2026.03 | 75.59 | |
| Chronos2# Parameters=120M, # Time Points=242.8B, Evaluation Protocol=linear-probing2026.03 | 75.02 | |
| Statistical MLEvaluation Protocol=linear-probing2026.03 | 72.43 | |
| Normwear# Parameters=136M, # Time Points=0.31B, Evaluation Protocol=linear-probing2026.03 | 70.77 | |
| TF-C# Parameters=12M, # Time Points=1.72M, Evaluation Protocol=linear-probing2026.03 | 55.39 | |
| SimMTM# Parameters=0.5M, # Time Points=1.72M, Evaluation Protocol=linear-probing2026.03 | 44.93 |