当前位置: X-MOL 学术Comput. Animat. Virtual Worlds › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Densely connected GCN model for motion prediction
Computer Animation and Virtual Worlds ( IF 0.9 ) Pub Date : 2020-07-01 , DOI: 10.1002/cav.1958
Yanran Li 1 , Lingteng Qiu 2 , Li Wang 1 , Fangde Liu 3 , Zhao Wang 4 , Sebastian Iulian Poiana 5 , Xiaosong Yang 1 , Jianjun Zhang 1
Affiliation  

Human motion prediction is a fundamental problem in understanding human natural movements. This task is very challenging due to the complex human body constraints and diversity of action types. Due to the human body being a natural graph, graph convolutional network (GCN)‐based models perform better than the traditional recurrent neural network (RNN)‐based models on modeling the natural spatial and temporal dependencies lying in the motion data. In this paper, we develop the GCN‐based models further by adding densely connected links to increase their feature utilizations and address oversmoothing problem. More specifically, the GCN block is used to learn the spatial relationships between the nodes and each feature map of the GCN block propagates directly to every following block as input rather than residual linked. In this way, the spatial dependency of human motion data is exploited more sufficiently and the features of different level of scale are fused more efficiently. Extensive experiments demonstrate our model achieving the state‐of‐the‐art results on CMU dataset.

中文翻译:

用于运动预测的密集连接 GCN 模型

人体运动预测是理解人体自然运动的基本问题。由于复杂的人体约束和动作类型的多样性,这项任务非常具有挑战性。由于人体是一个自然图,基于图卷积网络 (GCN) 的模型在建模运动数据中的自然空间和时间依赖性方面比传统的基于循环神经网络 (RNN) 的模型表现更好。在本文中,我们通过添加密集连接的链接来进一步开发基于 GCN 的模型,以提高其特征利用率并解决过度平滑问题。更具体地说,GCN 块用于学习节点之间的空间关系,并且 GCN 块的每个特征图作为输入直接传播到每个后续块而不是残差链接。这样,更充分地利用人体运动数据的空间依赖性,更有效地融合不同尺度级别的特征。大量实验证明我们的模型在 CMU 数据集上取得了最先进的结果。
更新日期:2020-07-01
down
wechat
bug