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.
Beyond Confusion: A Fine-grained Dialectical Examination of Human Activity Recognition Benchmark Datasets
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
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.
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.
-
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.