Efficient Unsupervised Temporal Segmentation of Human Motion

Simple item page
dc.contributor.authorVögele, Annaen_US
dc.contributor.authorKrüger, Björnen_US
dc.contributor.authorKlein, Reinharden_US
dc.contributor.editorVladlen Koltun and Eftychios Sifakisen_US
dc.date.accessioned2014-12-16T07:34:57Z
dc.date.available2014-12-16T07:34:57Z
dc.date.issued2014en_US
dc.description.abstractThis work introduces an efficient method for fully automatic temporal segmentation of human motion sequences and similar time series. The method relies on a neighborhood graph to partition a given data sequence into distinct activities and motion primitives according to self-similar structures given in that input sequence. In particular, the fast detection of repetitions within the discovered activity segments is a crucial problem of any motion processing pipeline directed at motion analysis and synthesis. The same similarity information in the neighborhood graph is further exploited to cluster these primitives into larger entities of semantic significance. The elements subject to this classification are then used as prior for estimating the same target values for entirely unknown streams of data. The technique makes no assumptions about the motion sequences at hand and no user interaction is required for the segmentation or clustering. Tests of our techniques are conducted on the CMU and HDM05 motion capture databases demonstrating the capability of our system handling motion segmentation, clustering, motion synthesis and transfer-of-label problems in practice - the latter being an optional step which relies on the preexistence of a small set of labeled data.en_US
dc.description.seriesinformationEurographics/ ACM SIGGRAPH Symposium on Computer Animationen_US
dc.identifier.isbn978-3-905674-61-3en_US
dc.identifier.issn1727-5288en_US
dc.identifier.urihttp://dx.doi.org/10.2312/sca.20141135en_US
dc.identifier.urihttp://hdl.handle.net/10.2312/sca.20141135.167-176
dc.publisherThe Eurographics Associationen_US
dc.subjectI.3.7 [Computer Graphics]en_US
dc.subjectThree Dimensional Graphics and Realismen_US
dc.subjectAnimationen_US
dc.titleEfficient Unsupervised Temporal Segmentation of Human Motionen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
167-176.pdf
Size:
6.28 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
supplemental.pdf
Size:
1.81 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
2014_sca_segmentation_resize.avi
Size:
47.66 MB
Format:
Unknown data format
Download
Collections
SCA 14: Eurographics/SIGGRAPH Symposium on Computer Animation