Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognition
This addresses limitations in activity recognition for applications where temporal and causal patterns are unknown, though it appears incremental as an enhancement to existing BoW methods.
The paper tackled the problem of recognizing complex long-term activities by augmenting Bag-of-Words models to capture temporal and structural information, demonstrating effectiveness in recognizing activities and detecting anomalies across four datasets.
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.