Human behaviour recognition in data-scarce domains

@article{Baxter2015HumanBR,
  title={Human behaviour recognition in data-scarce domains},
  author={Rolf Baxter and Neil Martin Robertson and David M. Lane},
  journal={Pattern Recognition},
  year={2015},
  volume={48},
  pages={2377-2393}
}
This paper presents the novel theory for performing multi-agent activity recognition without requiring large training corpora. The reduced need for data means that robust probabilistic recognition can be performed within domains where annotated datasets are traditionally unavailable. Complex human activities are composed from sequences of underlying primitive activities. We do not assume that the exact temporal ordering of primitives is necessary, so can represent complex activity using an… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 68 references

An overview of the pets 2006 dataset

D. Thirde, L. Li, J. Ferryman
in: International Workshop on Performance Evaluation of Tracking and Surveillance • 2006
View 19 Excerpts
Highly Influenced

Semantic Model Vectors for Complex Video Event Recognition

IEEE Transactions on Multimedia • 2012
View 7 Excerpts
Highly Influenced

Policy recognition in the abstract hidden Markov model

J. Artif. Intell. Res. • 2002
View 11 Excerpts
Highly Influenced

Detecting Social Groups in Crowded Surveillance Videos Using Visual Attention

2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops • 2014
View 1 Excerpt

A

J. Ferryman, D. Hogg, J. Sochman
Behera, J.a. Rodriguez-Serrano, S. Worgan, L. Li, V. Leung, M. Evans, P. Cornic, S. Herbin, S. Schlenger, M. Dose, Robust abandoned object detection integrating wide area visual surveillance and social context, Pattern Recognit. Lett. 34 (7) • 2013
View 3 Excerpts

Complex Event Detection via Multi-source Video Attributes

2013 IEEE Conference on Computer Vision and Pattern Recognition • 2013

Similar Papers

Loading similar papers…