Journal article
SkeletonNet: Mining Deep Part Features for 3-D Action Recognition
IEEE Signal Processing Letters, Vol.24(6), pp.731-735
2017
Abstract
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
Details
- Title
- SkeletonNet: Mining Deep Part Features for 3-D Action Recognition
- Authors/Creators
- Q. Ke (Author/Creator)S. An (Author/Creator)M. Bennamoun (Author/Creator)F. Sohel (Author/Creator)F. Boussaid (Author/Creator)
- Publication Details
- IEEE Signal Processing Letters, Vol.24(6), pp.731-735
- Publisher
- IEEE
- Identifiers
- 991005542470907891
- Copyright
- © 1994-2012 IEEE.
- Murdoch Affiliation
- School of Engineering and Information Technology
- Language
- English
- Resource Type
- Journal article
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites
Metrics
34 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- Citation topics
- 4 Electrical Engineering, Electronics & Computer Science
- 4.116 Robotics
- 4.116.1097 Gesture Recognition
- Web Of Science research areas
- Engineering, Electrical & Electronic
- ESI research areas
- Engineering