File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Action recognition using context and appearance distribution features

TitleAction recognition using context and appearance distribution features
Authors
Issue Date2011
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011, p. 489-496 How to Cite?
AbstractWe first propose a new spatio-temporal context distribution feature of interest points for human action recognition. Each action video is expressed as a set of relative XYT coordinates between pairwise interest points in a local region. We learn a global GMM (referred to as Universal Background Model, UBM) using the relative coordinate features from all the training videos, and then represent each video as the normalized parameters of a video-specific GMM adapted from the global GMM. In order to capture the spatio-temporal relationships at different levels, multiple GMMs are utilized to describe the context distributions of interest points over multi-scale local regions. To describe the appearance information of an action video, we also propose to use GMM to characterize the distribution of local appearance features from the cuboids centered around the interest points. Accordingly, an action video can be represented by two types of distribution features: 1) multiple GMM distributions of spatio-temporal context; 2) GMM distribution of local video appearance. To effectively fuse these two types of heterogeneous and complementary distribution features, we additionally propose a new learning algorithm, called Multiple Kernel Learning with Augmented Features (AFMKL), to learn an adapted classifier based on multiple kernels and the pre-learned classifiers of other action classes. Extensive experiments on KTH, multi-view IXMAS and complex UCF sports datasets demonstrate that our method generally achieves higher recognition accuracy than other state-of-the-art methods. © 2011 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/321446
ISSN
2023 SCImago Journal Rankings: 10.331

 

DC FieldValueLanguage
dc.contributor.authorWu, Xinxiao-
dc.contributor.authorXu, Dong-
dc.contributor.authorDuan, Lixin-
dc.contributor.authorLuo, Jiebo-
dc.date.accessioned2022-11-03T02:18:59Z-
dc.date.available2022-11-03T02:18:59Z-
dc.date.issued2011-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011, p. 489-496-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/321446-
dc.description.abstractWe first propose a new spatio-temporal context distribution feature of interest points for human action recognition. Each action video is expressed as a set of relative XYT coordinates between pairwise interest points in a local region. We learn a global GMM (referred to as Universal Background Model, UBM) using the relative coordinate features from all the training videos, and then represent each video as the normalized parameters of a video-specific GMM adapted from the global GMM. In order to capture the spatio-temporal relationships at different levels, multiple GMMs are utilized to describe the context distributions of interest points over multi-scale local regions. To describe the appearance information of an action video, we also propose to use GMM to characterize the distribution of local appearance features from the cuboids centered around the interest points. Accordingly, an action video can be represented by two types of distribution features: 1) multiple GMM distributions of spatio-temporal context; 2) GMM distribution of local video appearance. To effectively fuse these two types of heterogeneous and complementary distribution features, we additionally propose a new learning algorithm, called Multiple Kernel Learning with Augmented Features (AFMKL), to learn an adapted classifier based on multiple kernels and the pre-learned classifiers of other action classes. Extensive experiments on KTH, multi-view IXMAS and complex UCF sports datasets demonstrate that our method generally achieves higher recognition accuracy than other state-of-the-art methods. © 2011 IEEE.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titleAction recognition using context and appearance distribution features-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2011.5995624-
dc.identifier.scopuseid_2-s2.0-80052908096-
dc.identifier.spage489-
dc.identifier.epage496-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats