Abstract: Sensor-based Human Activity Recognition (HAR) often breaks down in real-world deployments because models entangle intrinsic activity patterns with extrinsic nuisance factors such as sensor ...
Abstract: In sensor-based human activity recognition (HAR), the annotation cost for sensor data is higher compared to data, such as images. One can use semisupervised learning (semi-SL) to reduce ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results