Skip to main content

Densely connected GCN model for motion prediction.

Liu, Y., Qiu, L., Wang, L., Liu, F., Wang, Z., Iulian Poiana, S., Yang, X. and Zhang, J. J., 2020. Densely connected GCN model for motion prediction. Computer Animation and Virtual Worlds, e1958.

Full text available as:

cav.1958.pdf - Published Version
Available under License Creative Commons Attribution.


DOI: 10.1002/cav.1958


© 2020 The Authors. Computer Animation and Virtual Worlds published by John Wiley & Sons, Ltd. 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.

Item Type:Article
Uncontrolled Keywords:densely, GCN, motion prediction, Spatial temporal
Group:Faculty of Media & Communication
ID Code:34529
Deposited By: Symplectic RT2
Deposited On:08 Sep 2020 16:14
Last Modified:14 Mar 2022 14:24


Downloads per month over past year

More statistics for this item...
Repository Staff Only -