Show simple item record

dc.contributor.authorKe, Q.
dc.contributor.authorBennamoun, M.
dc.contributor.authorAn, Senjian
dc.contributor.authorSohel, F.
dc.contributor.authorBoussaid, F.
dc.date.accessioned2018-08-08T04:43:22Z
dc.date.available2018-08-08T04:43:22Z
dc.date.created2018-08-08T03:50:34Z
dc.date.issued2018
dc.identifier.citationKe, Q. and Bennamoun, M. and An, S. and Sohel, F. and Boussaid, F. 2018. Learning Clip Representations for Skeleton-Based 3D Action Recognition. IEEE Transactions on Image Processing. 27 (6): pp. 2842-2855.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/70054
dc.identifier.doi10.1109/TIP.2018.2812099
dc.description.abstract

This paper presents a new representation of skeleton sequences for 3D action recognition. Existing methods based on hand-crafted features or recurrent neural networks cannot adequately capture the complex spatial structures and the long-term temporal dynamics of the skeleton sequences, which are very important to recognize the actions. In this paper, we propose to transform each channel of the 3D coordinates of a skeleton sequence into a clip. Each frame of the generated clip represents the temporal information of the entire skeleton sequence and one particular spatial relationship between the skeleton joints. The entire clip incorporates multiple frames with different spatial relationships, which provide useful spatial structural information of the human skeleton. We also propose a multitask convolutional neural network (MTCNN) to learn the generated clips for action recognition. The proposed MTCNN processes all the frames of the generated clips in parallel to explore the spatial and temporal information of the skeleton sequences. The proposed method has been extensively tested on six challenging benchmark datasets. Experimental results consistently demonstrate the superiority of the proposed clip representation and the feature learning method for 3D action recognition compared to the existing techniques.

dc.publisherIEEE
dc.titleLearning Clip Representations for Skeleton-Based 3D Action Recognition
dc.typeJournal Article
dcterms.source.volume27
dcterms.source.number6
dcterms.source.startPage2842
dcterms.source.endPage2855
dcterms.source.issn1057-7149
dcterms.source.titleIEEE Transactions on Image Processing
curtin.departmentSchool of Electrical Engineering, Computing and Mathematical Science (EECMS)
curtin.accessStatusFulltext not available


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record