Publications

@article{Kalayeh2015c,

title = {Understanding trajectory behavior: A motion pattern approach},

author = {Mahdi M Kalayeh and Stephen Mussmann and Alla Petrakova and Niels Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/1501.00614.pdf},

doi = {https://doi.org/10.48550/arXiv.1501.00614},

year  = {2015},

date = {2015-01-04},

urldate = {2015-01-04},

journal = {arXiv},

abstract = {Mining the underlying patterns in gigantic and complex data is of great importance to data analysts. In this paper, we propose a motion pattern approach to mine frequent behaviors in trajectory data. Motion patterns, defined by a set of highly similar flow vector groups in a spatial locality, have been shown to be very effective in extracting dominant motion behaviors in video sequences. Inspired by applications and properties of motion patterns, we have designed a framework that successfully solves the general task of trajectory clustering. Our proposed algorithm consists of four phases: flow vector computation, motion component extraction, motion component's reachability set creation, and motion pattern formation. For the first phase, we break down trajectories into flow vectors that indicate instantaneous movements. In the second phase, via a Kmeans clustering approach, we create motion components by clustering the flow vectors with respect to their location and velocity. Next, we create motion components' reachability set in terms of spatial proximity and motion similarity. Finally, for the fourth phase, we cluster motion components using agglomerative clustering with the weighted Jaccard distance between the motion components' signatures, a set created using path reachability. We have evaluated the effectiveness of our proposed method in an extensive set of experiments on diverse datasets. Further, we have shown how our proposed method handles difficulties in the general task of trajectory clustering that challenge the existing state-of-the-art methods.},

keywords = {Motion Patterns},

pubstate = {published},

tppubtype = {article}

}

@article{Kalayeh2015cb,

title = {Understanding trajectory behavior: A motion pattern approach},

author = {Mahdi M Kalayeh and Stephen Mussmann and Alla Petrakova and Niels Vitoria Lobo and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/1501.00614.pdf},

doi = {https://doi.org/10.48550/arXiv.1501.00614},

year  = {2015},

date = {2015-01-04},

urldate = {2015-01-04},

journal = {arXiv},

abstract = {Mining the underlying patterns in gigantic and complex data is of great importance to data analysts. In this paper, we propose a motion pattern approach to mine frequent behaviors in trajectory data. Motion patterns, defined by a set of highly similar flow vector groups in a spatial locality, have been shown to be very effective in extracting dominant motion behaviors in video sequences. Inspired by applications and properties of motion patterns, we have designed a framework that successfully solves the general task of trajectory clustering. Our proposed algorithm consists of four phases: flow vector computation, motion component extraction, motion component's reachability set creation, and motion pattern formation. For the first phase, we break down trajectories into flow vectors that indicate instantaneous movements. In the second phase, via a Kmeans clustering approach, we create motion components by clustering the flow vectors with respect to their location and velocity. Next, we create motion components' reachability set in terms of spatial proximity and motion similarity. Finally, for the fourth phase, we cluster motion components using agglomerative clustering with the weighted Jaccard distance between the motion components' signatures, a set created using path reachability. We have evaluated the effectiveness of our proposed method in an extensive set of experiments on diverse datasets. Further, we have shown how our proposed method handles difficulties in the general task of trajectory clustering that challenge the existing state-of-the-art methods.},

keywords = {Motion Patterns},

pubstate = {published},

tppubtype = {article}

}

@article{Khokhar2013,

title = {Multi-agent event recognition by preservation of spatiotemporal relationships between probabilistic models},

author = {Salman Khokhar and Imran Saleemi and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/ivcCopyFinal.pdf 

http://dx.doi.org/10.1016/j.imavis.2013.06.004},

year  = {2013},

date = {2013-01-29},

urldate = {2013-01-29},

journal = {Image and Vision Computing},

keywords = {Deep Learning, Human Action and Activity Recognition, Motion Patterns},

pubstate = {published},

tppubtype = {article}

}

@article{Khokhar2013b,

title = {Multi-agent event recognition by preservation of spatiotemporal relationships between probabilistic models},

author = {Salman Khokhar and Imran Saleemi and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/ivcCopyFinal.pdf 

http://dx.doi.org/10.1016/j.imavis.2013.06.004},

year  = {2013},

date = {2013-01-29},

urldate = {2013-01-29},

journal = {Image and Vision Computing},

keywords = {Deep Learning, Human Action and Activity Recognition, Motion Patterns},

pubstate = {published},

tppubtype = {article}

}

@article{Saleemi2009,

title = {Probabilistic Modeling of Scene Dynamics for Applications in VIsual Surveillance},

author = {Imran Saleemi and Khurram Shafique and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/TPAMI_scene_dynamics.pdf},

year  = {2009},

date = {2009-01-29},

urldate = {2009-01-29},

journal = {IEEE TPAMI},

keywords = {Abnormal Event Detection, Anomaly Detection, Deep Learning, Motion Patterns},

pubstate = {published},

tppubtype = {article}

}

@article{Saleemi2009b,

title = {Probabilistic Modeling of Scene Dynamics for Applications in VIsual Surveillance},

author = {Imran Saleemi and Khurram Shafique and Mubarak Shah},

url = {https://www.crcv.ucf.edu/papers/TPAMI_scene_dynamics.pdf},

year  = {2009},

date = {2009-01-29},

urldate = {2009-01-29},

journal = {IEEE TPAMI},

keywords = {Abnormal Event Detection, Anomaly Detection, Deep Learning, Motion Patterns},

pubstate = {published},

tppubtype = {article}

}