MCSTN learns corruption-invariant representations by enforcing consistency across dual-level simulated corruptions using a dual-stream spatio-temporal architecture for robust sensor-based HAR.
MaskCAE: Masked convolutional AutoEncoder via sensor data reconstruction for self-supervised human activity recognition
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
-
Leveraging Imperfect Medical Data: A Manifold-Consistent Spatio-Temporal Network for Sensor-based Human Activity Recognition
MCSTN learns corruption-invariant representations by enforcing consistency across dual-level simulated corruptions using a dual-stream spatio-temporal architecture for robust sensor-based HAR.