In this paper we are interested in recognizing human actions from sequences of 3D skeleton data. For this purpose we combine a 3D Convolutional Neural Network with body representations based on Euclidean Distance Matrices (EDMs), which have been recently shown to be very effective to capture the geometric structure of the human pose. One inherent limitation of the EDMs, however, is that they are defined up to a permutation of the skeleton joints, i.e., randomly shuffling the ordering of the joints yields many different representations. In oder to address this issue we introduce a novel architecture that simultaneously, and in an end-to-end manner, learns an optimal transformation of the joints, while optimizing the rest of parameters of the convolutional network. The proposed approach achieves state-of-the-art results on 3 benchmarks, including the recent NTU RGB-D dataset, for which we improve on previous LSTM-based methods by more than 10 percentage points, also surpassing other CNN-based methods while using almost 1000 times fewer parameters. ; Peer Reviewed ; Postprint (author's final draft)


    Zugriff

    Download


    Exportieren, teilen und zitieren



    3D CNNs on distance matrices for human action recognition

    Hernández Ruiz, Alejandro José / Porzi, Lorenzo / Rota Buló, Samuel et al. | BASE | 2017

    Freier Zugriff

    Cooperative environment recognition utilizing UWB waveforms and CNNs

    Mäkela, Maija / Rantanen, Jesperi / Ilinca, Julian et al. | BASE | 2020

    Freier Zugriff

    Emotion Recognition from 3D Motion Capture Data using Deep CNNs

    Haris Zacharatos / Christos Gatzoulis / Panayiotis Charalambous et al. | BASE | 2021

    Freier Zugriff

    Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition

    Hu, Qichang / Wang, Huibing / Li, Teng et al. | IEEE | 2017