DecomposeWHAR, a decomposition-and-fusion model using depth-wise convolutions, Mamba, and self-attention, achieves state-of-the-art results on three wearable human activity recognition datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity Recognition
DecomposeWHAR, a decomposition-and-fusion model using depth-wise convolutions, Mamba, and self-attention, achieves state-of-the-art results on three wearable human activity recognition datasets.