Searching video for complex activities with finite state models

Simple item page
dc.contributor.authorİkizler, Nazlıen_US
dc.contributor.authorForsyth, D.en_US
dc.coverage.spatialMinneapolis, MN, USA
dc.date.accessioned2016-02-08T11:44:02Z
dc.date.available2016-02-08T11:44:02Z
dc.date.issued2007-06en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionDate of Conference: 17-22 June 2007
dc.descriptionConference name: IEEE Conference on Computer Vision and Pattern Recognition, 2007
dc.description.abstractWe describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach is based on units of activity at segments of the body, that can be composed across space and across the body to produce complex queries. The presence of search units is inferred automatically by tracking the body, lifting the tracks to 3D and comparing to models trained using motion capture data. We show results for a large range of queries applied to a collection of complex motion and activity. Our models of short time scale limb behaviour are built using labelled motion capture set. We compare with discriminative methods applied to tracker data; our method offers significantly improved performance. We show experimental evidence that our method is robust to view direction and is unaffected by the changes of clothing. © 2007 IEEE.en_US
dc.identifier.doi10.1109/CVPR.2007.383168en_US
dc.identifier.urihttp://hdl.handle.net/11693/27091
dc.language.isoEnglishen_US
dc.publisherIEEE
dc.relation.isversionofhttp://dx.doi.org/10.1109/CVPR.2007.383168en_US
dc.source.titleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognitionen_US
dc.subjectComputational methodsen_US
dc.subjectDiscriminant analysisen_US
dc.subjectMathematical modelsen_US
dc.subjectQuery languagesen_US
dc.subjectRobust controlen_US
dc.subjectThree dimensionalen_US
dc.subjectComplex activitiesen_US
dc.subjectDiscriminative methodsen_US
dc.subjectFinite state modelsen_US
dc.subjectMotion capture seten_US
dc.subjectMotion estimationen_US
dc.titleSearching video for complex activities with finite state modelsen_US
dc.typeConference Paperen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Searching video for complex activities with finite state models.pdf
Size:
1.13 MB
Format:
Adobe Portable Document Format
Description:
Full Printable Version
Download
Collections
Department of Computer Engineering