Show simple item record

dc.contributor.authorCiptadi, Arridhana
dc.contributor.authorGoodwin, Matthew S.
dc.contributor.authorRehg, James M.
dc.date.accessioned2015-06-23T15:35:09Z
dc.date.available2015-06-23T15:35:09Z
dc.date.issued2014
dc.identifier.citationCiptadi, A., Goodwin, M. S., & Rehg, J. M. (2014). “Movement Pattern Histogram for Action Recognition and Retrieval”. Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (Eds.). Computer Vision – ECCV 2014. 13th European Conference, Zurich Switzerland, 6-12 September 2014. Proceedings, Part II. In Lecture Notes in Computer Science, 2014, Vol. 8690, pp. 695-710.en_US
dc.identifier.isbn978-3-319-10604-5
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/1853/53667
dc.description© Springer International Publishing Switzerland 2014. The original publication is available at www.springerlink.comen_US
dc.descriptionDOI: 10.1007/978-3-319-10605-2_45
dc.description.abstractWe present a novel action representation based on encoding the global temporal movement of an action. We represent an action as a set of movement pattern histograms that encode the global temporal dynamics of an action. Our key observation is that temporal dynamics of an action are robust to variations in appearance and viewpoint changes, making it useful for action recognition and retrieval. We pose the problem of computing similarity between action representations as a maximum matching problem in a bipartite graph. We demonstrate the effectiveness of our method for cross-view action recognition on the IXMAS dataset. We also show how our representation complements existing bag- of-features representations on the UCF50 dataset. Finally we show the power of our representation for action retrieval on a new real-world dataset containing repetitive motor movements emitted by children with autism in an unconstrained classroom setting.en_US
dc.language.isoen_USen_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectAction recognitionen_US
dc.subjectAction retrievalen_US
dc.subjectBipartite graphen_US
dc.subjectDataseten_US
dc.subjectGlobal temporal movementen_US
dc.subjectMotor movementsen_US
dc.subjectMovement pattern histogramen_US
dc.titleMovement Pattern Histogram for Action Recognition and Retrievalen_US
dc.typeBook Chapteren_US
dc.typeProceedingsen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Institute for Robotics and Intelligent Machinesen_US
dc.contributor.corporatenameNortheastern University (Boston, Mass.). Department of Health Sciencesen_US
dc.publisher.originalSpringer International
dc.identifier.doi10.1007/978-3-319-10605-2_45
dc.embargo.termsnullen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record