%0 Book Section %1 springerlink:10.1007/978-3-540-76856-2_33 %A Connolly, Christopher %B Advances in Visual Computing %C Berlin / Heidelberg %D 2007 %E Bebis, George %E Boyle, Richard %E Parvin, Bahram %E Koracin, Darko %E Paragios, Nikos %E Tanveer, Syeda-Mahmood %E Ju, Tao %E Liu, Zicheng %E Coquillart, Sabine %E Cruz-Neira, Carolina %E Müller, Torsten %E Malzbender, Tom %I Springer %K data discovery knowledge mining prediction %P 340-348 %R 10.1007/978-3-540-76856-2_33 %T Learning to Recognize Complex Actions Using Conditional Random Fields %U http://dx.doi.org/10.1007/978-3-540-76856-2_33 %V 4842 %X Surveillance systems that operate continuously generate large volumes of data. One such system is described here, continuously tracking and storing observations taken from multiple stereo systems. Automated event recognition is one way of annotating track databases for faster search and retrieval. Recognition of complex events in such data sets often requires context for successful disambiguation of apparently similar activities. Conditional random fields permit straightforward incorporation of temporal context into the event recognition task. This paper describes experiments in activity learning, using conditional random fields to learn and recognize composite events that are captured by the observation stream.

@incollection{springerlink:10.1007/978-3-540-76856-2_33, abstract = {Surveillance systems that operate continuously generate large volumes of data. One such system is described here, continuously tracking and storing observations taken from multiple stereo systems. Automated event recognition is one way of annotating track databases for faster search and retrieval. Recognition of complex events in such data sets often requires context for successful disambiguation of apparently similar activities. Conditional random fields permit straightforward incorporation of temporal context into the event recognition task. This paper describes experiments in activity learning, using conditional random fields to learn and recognize composite events that are captured by the observation stream.}, added-at = {2010-11-08T18:28:26.000+0100}, address = {Berlin / Heidelberg}, affiliation = {SRI International, 333 Ravenswood Avenue, Menlo Park, CA}, author = {Connolly, Christopher}, biburl = {https://www.bibsonomy.org/bibtex/268139a819cb6da9e0e8a99f840eab503/atzmueller}, booktitle = {Advances in Visual Computing}, description = {SpringerLink - Abstract}, doi = {10.1007/978-3-540-76856-2_33}, editor = {Bebis, George and Boyle, Richard and Parvin, Bahram and Koracin, Darko and Paragios, Nikos and Tanveer, Syeda-Mahmood and Ju, Tao and Liu, Zicheng and Coquillart, Sabine and Cruz-Neira, Carolina and Müller, Torsten and Malzbender, Tom}, interhash = {e34ee779859c25e8cd6b8e24b74c1d23}, intrahash = {68139a819cb6da9e0e8a99f840eab503}, keywords = {data discovery knowledge mining prediction}, pages = {340-348}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2010-11-08T18:28:27.000+0100}, title = {Learning to Recognize Complex Actions Using Conditional Random Fields}, url = {http://dx.doi.org/10.1007/978-3-540-76856-2_33}, volume = 4842, year = 2007 }