Action2Activity: Recognizing Complex Activities from Sensor Data

TL;DR

This paper introduces a novel method for recognizing complex human activities from sensor data by combining temporal pattern mining and adaptive multi-task learning, effectively capturing activity-related features and their temporal relationships.

Contribution

It presents a new approach integrating temporal pattern mining with adaptive multi-task learning for complex activity recognition from sensor data.

Findings

Effective recognition of complex activities demonstrated on real-world data

Temporal pattern mining captures intrinsic activity properties

Adaptive multi-task learning improves discriminant feature selection

Abstract

As compared to simple actions, activities are much more complex, but semantically consistent with a human's real life. Techniques for action recognition from sensor generated data are mature. However, there has been relatively little work on bridging the gap between actions and activities. To this end, this paper presents a novel approach for complex activity recognition comprising of two components. The first component is temporal pattern mining, which provides a mid-level feature representation for activities, encodes temporal relatedness among actions, and captures the intrinsic properties of activities. The second component is adaptive Multi-Task Learning, which captures relatedness among activities and selects discriminant features. Extensive experiments on a real-world dataset demonstrate the effectiveness of our work.