Action2Activity: Recognizing Complex Activities from Sensor Data
This addresses the challenge of complex activity recognition for applications in human behavior analysis, but appears incremental as it builds on existing action recognition techniques.
The paper tackles the problem of recognizing complex activities from sensor data by bridging the gap between actions and activities, using temporal pattern mining and adaptive multi-task learning, with experiments on a real-world dataset showing effectiveness.
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.