Action recognition is widely used in human-computer interaction, intelligent monitoring and other applications. Recently, more and more researcher pay attention to it. While, skeleton-based action recognition is more and more popular because of its low cost and robustness. Current good performance methods based on skeleton is supervised mostly, which needs large labeled datasets for train. But for some special task, such as the pedestrian action recognition of unmanned driving in real traffic scene, it is difficult to gain the labeled action data because the large cost of time, money and energy. Therefore, we proposed a Bi-GRU-Attention Enhanced Unsupervised Network (BGAEUN) for action recognition based on skeleton sequence. BGAEUN adopts an encoder-decoder network, and adds an attention mechanism in the encode, learns the weights of the hidden state, and obtains the weights of different skeleton nodes, so that it can better characterize actions and provide better skeleton features. For the decoder, using fixed weight and fixed state strategies to weaken the decoder, calculate the loss of the output and input of the decoder, minimize the loss, make it similar to the input, and minimize the reconstruction loss in the training process. BGAEUN exploits the last layer feature of encoder to classify by k-nearest neighbors algorithm. Experiments on large-scale action dataset NTU-RGB + D show BGAEUN achieves a higher recognition accuracy than current most unsupervised skeleton action recognition methods.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Bi-GRU-Attention Enhanced Unsupervised Network for Skeleton-Based Action Recognition


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Wu, Meiping (editor) / Niu, Yifeng (editor) / Gu, Mancang (editor) / Cheng, Jin (editor) / Chen, Li (author) / Ma, Nan (author) / Zhang, Guoping (author)

    Conference:

    International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021



    Publication date :

    2022-03-18


    Size :

    9 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Unsupervised Hyperbolic Action Recognition

    Castro-Vargas, John-Alejandro / Garcia-Garcia, Alberto / Martinez-Gonzalez, Pablo et al. | Springer Verlag | 2022


    Improved ELBO-assisted Transformer for Skeleton-Based Action Recognition

    Bhattacharjee, Arnab / Chen, Wen-Hui / Lin, Yu-Chen et al. | IEEE | 2023


    Driver-Skeleton: A Dataset for Driver Action Recognition

    Lin, Zeyang / Liu, Yinchuan / Zhang, Xuetao | IEEE | 2021


    Skeleton driven action recognition using an image-based spatial-temporal representation and convolution neural network

    Silva, Vinícius / Soares, Filomena / Leão, Celina Pinto et al. | BASE | 2021

    Free access

    A Novel Spatial-Temporal Graph for Skeleton-based Driver Action Recognition

    Li, Peng / Lu, Meiqi / Zhang, Zhiwei et al. | IEEE | 2019