A large-scale benchmark of 17 WHAR models across 30 datasets finds predictive performance has plateaued while efficiency favors compact neural models and random forests on the Pareto frontier.
Reyes-Ortiz, Luca Oneto, Albert Samà, Xavier Parra, and Davide An- guita
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A gradient-free framework adapts pretrained HAR classifiers to new users via Bayesian prototype updates in prototypical networks, improving F1 scores with 3s calibration data.
citing papers explorer
-
WHAR Arena: Benchmarking the State of the Art in Efficient Wearable Human Activity Recognition
A large-scale benchmark of 17 WHAR models across 30 datasets finds predictive performance has plateaued while efficiency favors compact neural models and random forests on the Pareto frontier.
-
Uncertainty-Aware (Un)Supervised Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition
A gradient-free framework adapts pretrained HAR classifiers to new users via Bayesian prototype updates in prototypical networks, improving F1 scores with 3s calibration data.