# Learning Multi-level Features For Sensor-based Human Action Recognition

arXiv: https://arxiv.org/abs/1611.07143 · HTML: https://mlsanity.com/paper/1611.07143/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2016.

## Built on by (most cited first, 2 of 2)

- [Attention-Based Sensor Fusion for Human Activity Recognition Using IMU Signals](https://mlsanity.com/paper/2112.11224/) (2021)
- [Motion-R3: Fast and Accurate Motion Annotation via Representation-based Representativeness Ranking](https://mlsanity.com/paper/2304.01672/) (2023)

## Abstract (arXiv)

This paper proposes a multi-level feature learning framework for human action recognition using a single body-worn inertial sensor. The framework consists of three phases, respectively designed to analyze signal-based (low-level), components (mid-level) and semantic (high-level) information. Low-level features capture the time and frequency domain property while mid-level representations learn the composition of the action. The Max-margin Latent Pattern Learning (MLPL) method is proposed to learn high-level semantic descriptions of latent action patterns as the output of our framework. The proposed method achieves the state-of-the-art performances, 88.7%, 98.8% and 72.6% (weighted F1 score) respectively, on Skoda, WISDM and OPP datasets.