dc.contributor.author | Danelakis, Antonios | |
dc.contributor.author | Theoharis, Theoharis | |
dc.contributor.author | Pratikakis, Ioannis | |
dc.date.accessioned | 2019-05-13T08:51:13Z | |
dc.date.available | 2019-05-13T08:51:13Z | |
dc.date.created | 2018-09-28T16:02:34Z | |
dc.date.issued | 2018 | |
dc.identifier.citation | Multimedia tools and applications. 2018, 77 24813-24841. | nb_NO |
dc.identifier.issn | 1380-7501 | |
dc.identifier.uri | http://hdl.handle.net/11250/2597354 | |
dc.description.abstract | This work introduces a new scheme for action unit detection in 3D facial videos. Sets of features that define action unit activation in a robust manner are proposed. These features are computed based on eight detected facial landmarks on each facial mesh that involve angles, areas and distances. Support vector machine classifiers are then trained using the above features in order to perform action unit detection. The proposed AU detection scheme is used in a dynamic 3D facial expression retrieval and recognition pipeline, highlighting the most important AU s, in terms of providing facial expression information, and at the same time, resulting in better performance than state-of-the-art methodologies. | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | Springer Verlag | nb_NO |
dc.title | Action unit detection in 3D facial videos with application in facial expression retrieval and recognition | nb_NO |
dc.type | Journal article | nb_NO |
dc.type | Peer reviewed | nb_NO |
dc.description.version | acceptedVersion | nb_NO |
dc.source.pagenumber | 24813-24841 | nb_NO |
dc.source.volume | 77 | nb_NO |
dc.source.journal | Multimedia tools and applications | nb_NO |
dc.identifier.doi | 10.1007/s11042-018-5699-9 | |
dc.identifier.cristin | 1615915 | |
dc.description.localcode | This is a post-peer-review, pre-copyedit version of an article published in [Multimedia tools and applications]. The final authenticated version is available online at: https://doi.org/10.1007/s11042-018-5699-9 | nb_NO |
cristin.unitcode | 194,63,10,0 | |
cristin.unitname | Institutt for datateknologi og informatikk | |
cristin.ispublished | true | |
cristin.fulltext | preprint | |
cristin.qualitycode | 1 | |