dc.contributor.authorYuan, Junsong
dc.contributor.authorLiu, Zicheng
dc.contributor.authorWu, Ying
dc.date.accessioned2013-12-06T04:44:41Z
dc.date.available2013-12-06T04:44:41Z
dc.date.copyright2011en_US
dc.date.issued2011
dc.identifier.citationYuan,J., Liu, Z., & Wu,Y. (2011) Discriminative Video Pattern Search for Efficient Action Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 33, 1728-1743.en_US
dc.identifier.issn0162-8828en_US
dc.identifier.urihttp://hdl.handle.net/10220/18133
dc.description.abstractActions are spatiotemporal patterns. Similar to the sliding window-based object detection, action detection finds the reoccurrences of such spatiotemporal patterns through pattern matching, by handling cluttered and dynamic backgrounds and other types of action variations. We address two critical issues in pattern matching-based action detection: 1) the intrapattern variations in actions, and 2) the computational efficiency in performing action pattern search in cluttered scenes. First, we propose a discriminative pattern matching criterion for action classification, called naive Bayes mutual information maximization (NBMIM). Each action is characterized by a collection of spatiotemporal invariant features and we match it with an action class by measuring the mutual information between them. Based on this matching criterion, action detection is to localize a subvolume in the volumetric video space that has the maximum mutual information toward a specific action class. A novel spatiotemporal branch-and-bound (STBB) search algorithm is designed to efficiently find the optimal solution. Our proposed action detection method does not rely on the results of human detection, tracking, or background subtraction. It can handle action variations such as performing speed and style variations as well as scale changes well. It is also insensitive to dynamic and cluttered backgrounds and even to partial occlusions. The cross-data set experiments on action detection, including KTH, CMU action data sets, and another new MSR action data set, demonstrate the effectiveness and efficiency of the proposed multiclass multiple-instance action detection method. [This work was supported in part by the Nanyang Assistant Professorship to Dr. Junsong Yuan, the National Science Foundation grant IIS-0347877, IIS-0916607, and US Army Research Laboratory and the US Army Research Office under grant ARO W911NF-08-1-0504.]en_US
dc.format.extent17 p.en_US
dc.language.isoenen_US
dc.relation.ispartofseriesIEEE transactions on pattern analysis and machine intelligenceen_US
dc.rights© 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: http://dx.doi.org/doi:10.1109/TPAMI.2011.38 .en_US
dc.subjectElectrical and Electronic Engineering
dc.titleDiscriminative video pattern search for efficient action detectionen_US
dc.typeJournal Article
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.identifier.doihttp://dx.doi.org/doi:10.1109/TPAMI.2011.38
dc.description.versionAccepted versionen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record