BabyMamba-HAR develops lightweight SSM architectures for HAR that match prior accuracy with 11x fewer MACs on high-channel data and deploy successfully on ESP32 and Raspberry Pi Pico with high parity.
LHAR: Lightweight Human Activity Recognition on Knowledge Dis- tillation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BabyMamba-HAR: Lightweight Selective State Space Models for Efficient Human Activity Recognition on Resource Constrained Devices
BabyMamba-HAR develops lightweight SSM architectures for HAR that match prior accuracy with 11x fewer MACs on high-channel data and deploy successfully on ESP32 and Raspberry Pi Pico with high parity.