BenchHAR finds that hybrid reconstruction-plus-contrastive SSL with CNN encoders generalizes best for sensor HAR but overall performance on unseen distributions remains unsatisfactory.
Capture-24: A large dataset of wrist-worn activity tracker data collected in the wild for human activity recognition.Scientific Data, 11(1):1135
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition
BenchHAR finds that hybrid reconstruction-plus-contrastive SSL with CNN encoders generalizes best for sensor HAR but overall performance on unseen distributions remains unsatisfactory.