MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction

doi:doi:10.57702/1sy1f2qa

MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction

Human motion prediction is a challenging task due to the stochasticity and aperiodicity of future poses. Recently, graph convolutional network has been proven to be very effective to learn dynamic relations among pose joints, which is helpful for pose prediction. On the other hand, one can abstract a human pose recursively to obtain a set of poses at multiple scales. With the increase of the abstraction level, the motion of the pose becomes more stable, which benefits pose prediction too.

BibTex:

@dataset{Lingwei_Dang_and_Yongwei_Nie_and_Chengjiang_Long_and_Qing_Zhang_and_Guiqing_Li_2024,
    abstract = {Human motion prediction is a challenging task due to the stochasticity and aperiodicity of future poses. Recently, graph convolutional network has been proven to be very effective to learn dynamic relations among pose joints, which is helpful for pose prediction. On the other hand, one can abstract a human pose recursively to obtain a set of poses at multiple scales. With the increase of the abstraction level, the motion of the pose becomes more stable, which benefits pose prediction too.},
    author = {Lingwei Dang and Yongwei Nie and Chengjiang Long and Qing Zhang and Guiqing Li},
    doi = {10.57702/1sy1f2qa},
    institution = {No Organization},
    keyword = {'graph convolutional network', 'human motion prediction', 'multi-scale', 'residual'},
    month = {dec},
    publisher = {TIB},
    title = {MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction},
    url = {https://service.tib.eu/ldmservice/dataset/msr-gcn--multi-scale-residual-graph-convolution-networks-for-human-motion-prediction},
    year = {2024}
}