SkeletonNet: Mining Deep Part Features for 3-D Action Recognition
This letter presents SkeletonNet, a deep learning framework for skeleton-based 3-D action recognition. Given a skeleton sequence, the spatial structure of the skeleton joints in each frame and the temporal information between multiple frames are two important factors for action recognition. We first...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal Article |
| Published: |
Institute of Electrical and Electronics Engineers
2017
|
| Online Access: | http://hdl.handle.net/20.500.11937/69968 |
| _version_ | 1848762181013733376 |
|---|---|
| author | Ke, Q. An, Senjian Bennamoun, M. Sohel, F. Boussaid, F. |
| author_facet | Ke, Q. An, Senjian Bennamoun, M. Sohel, F. Boussaid, F. |
| author_sort | Ke, Q. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This letter presents SkeletonNet, a deep learning framework for skeleton-based 3-D action recognition. Given a skeleton sequence, the spatial structure of the skeleton joints in each frame and the temporal information between multiple frames are two important factors for action recognition. We first extract body-part-based features from each frame of the skeleton sequence. Compared to the original coordinates of the skeleton joints, the proposed features are translation, rotation, and scale invariant. To learn robust temporal information, instead of treating the features of all frames as a time series, we transform the features into images and feed them to the proposed deep learning network, which contains two parts: one to extract general features from the input images, while the other to generate a discriminative and compact representation for action recognition. The proposed method is tested on the SBU kinect interaction dataset, the CMU dataset, and the large-scale NTU RGB+D dataset and achieves state-of-the-art performance. |
| first_indexed | 2025-11-14T10:43:29Z |
| format | Journal Article |
| id | curtin-20.500.11937-69968 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T10:43:29Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-699682019-01-24T02:48:38Z SkeletonNet: Mining Deep Part Features for 3-D Action Recognition Ke, Q. An, Senjian Bennamoun, M. Sohel, F. Boussaid, F. This letter presents SkeletonNet, a deep learning framework for skeleton-based 3-D action recognition. Given a skeleton sequence, the spatial structure of the skeleton joints in each frame and the temporal information between multiple frames are two important factors for action recognition. We first extract body-part-based features from each frame of the skeleton sequence. Compared to the original coordinates of the skeleton joints, the proposed features are translation, rotation, and scale invariant. To learn robust temporal information, instead of treating the features of all frames as a time series, we transform the features into images and feed them to the proposed deep learning network, which contains two parts: one to extract general features from the input images, while the other to generate a discriminative and compact representation for action recognition. The proposed method is tested on the SBU kinect interaction dataset, the CMU dataset, and the large-scale NTU RGB+D dataset and achieves state-of-the-art performance. 2017 Journal Article http://hdl.handle.net/20.500.11937/69968 10.1109/LSP.2017.2690339 Institute of Electrical and Electronics Engineers restricted |
| spellingShingle | Ke, Q. An, Senjian Bennamoun, M. Sohel, F. Boussaid, F. SkeletonNet: Mining Deep Part Features for 3-D Action Recognition |
| title | SkeletonNet: Mining Deep Part Features for 3-D Action Recognition |
| title_full | SkeletonNet: Mining Deep Part Features for 3-D Action Recognition |
| title_fullStr | SkeletonNet: Mining Deep Part Features for 3-D Action Recognition |
| title_full_unstemmed | SkeletonNet: Mining Deep Part Features for 3-D Action Recognition |
| title_short | SkeletonNet: Mining Deep Part Features for 3-D Action Recognition |
| title_sort | skeletonnet: mining deep part features for 3-d action recognition |
| url | http://hdl.handle.net/20.500.11937/69968 |