Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Gesture Classification research benchmarks · SOTA2 Research

Gesture Classification

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Toro-Ossaba (Leave-One-Subject-Out (LOSO))

91.3Accuracy

10

May 6, 2026

Ninapro DB4 (Leave-One-Subject-Out (LOSO))

90.5Accuracy

10

May 6, 2026

EMG-EPN (Leave-One-Subject-Out (LOSO))

98.11Accuracy

10

May 6, 2026

ULB-MLG (Leave-One-Subject-Out (LOSO))

93.36Accuracy

10

May 6, 2026

Gesture Classification Benchmark 13-class (130 hand-crafted gesture samples)

100Accuracy

4

Jun 11, 2026

High-density sEMG dataset 65 gestures (5-fold cross-validation)

91.07Accuracy

4

Apr 7, 2026

88.32Accuracy (Room)

4

Mar 16, 2026

8-channel sEMG leave-two-subjects-out CV

90.6Accuracy

2

May 1, 2026

Popular datasets

NinaPro sEMG Widar High-density sEMG dataset ULB-MLG

Follow for updates

Join SOTA2 Contact