Browse by author
Lookup NU author(s): Dr Thomas Ploetz
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
We present data-driven techniques to augment Bag of Words (BoW) models, which allow for more robust modeling and recognition of complex 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.
Author(s): Bettadapura V, Schindler G, Ploetz T, Essa I
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: 26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013)
Year of Conference: 2013