SkeletonNet: Mining Deep Part Features for 3-D Action Recognition

    Research output: Contribution to journalArticlepeer-review

    140 Citations (Scopus)
    770 Downloads (Pure)


    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.
    Original languageEnglish
    Article number7891014
    Pages (from-to)731-735
    Number of pages5
    JournalIEEE Signal Processing Letters
    Issue number6
    Publication statusPublished - Jun 2017


    Dive into the research topics of 'SkeletonNet: Mining Deep Part Features for 3-D Action Recognition'. Together they form a unique fingerprint.

    Cite this