Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognition

TL;DR

This paper introduces data-driven methods to enhance Bag-of-Words models for activity recognition by capturing temporal and structural information, improving robustness in complex activity streams.

Contribution

It proposes novel techniques including the use of regular expressions to discover activity patterns, addressing limitations of standard BoW models in representing activity structure.

Findings

Effective activity recognition in four complex datasets

Successful anomaly detection in activity streams

Enhanced modeling of long-term activities

Abstract

We present data-driven techniques to augment Bag of Words (BoW) models, which allow for more robust modeling and recognition of complex long-term activities, especially when the structure and topology of the activities are not known a priori. Our approach specifically addresses the limitations of standard BoW approaches, which fail to represent the underlying temporal and causal information that is inherent in activity streams. In addition, we also propose the use of randomly sampled regular expressions to discover and encode patterns in activities. We demonstrate the effectiveness of our approach in experimental evaluations where we successfully recognize activities and detect anomalies in four complex datasets.