Show simple item record

dc.contributor.authorTiddeman, Bernarden_US
dc.contributor.authorHunter, Daviden_US
dc.contributor.authorPerrett, Daviden_US
dc.contributor.editorIan Grimstead and Hamish Carren_US
dc.date.accessioned2013-10-31T10:30:53Z
dc.date.available2013-10-31T10:30:53Z
dc.date.issued2011en_US
dc.identifier.isbn978-3-905673-83-8en_US
dc.identifier.urihttp://dx.doi.org/10.2312/LocalChapterEvents/TPCG/TPCG11/049-052en_US
dc.description.abstractIn this paper we present a prototype system for altering perceived attributes of faces in video sequences, such as the apparent age, sex or emotional state. The system uses multilinear models to decompose the parameters coding for each frame into separate pose and identity parameters. The multilinear model is learnt automatically from the training video data. Statistical models of group identity are then used to alter the identity parameters from one group to another (e.g. from male to female). An autoregressive model is learnt from the pose parameters, and this is applied to alter the dynamics. We have tested our system on a small dataset (for altering apparent gender) with encouraging preliminary results.en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectCategories and Subject Descriptors (according to ACM CCS): I.3.7 [Computer Graphics]: Three-Dimensional Graphics and Realism-Animationen_US
dc.titleDynamic Video Face Transformation Using Multilinear and Autoregressive Modelsen_US
dc.description.seriesinformationTheory and Practice of Computer Graphicsen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record