Human Action prediction based on skeleton data

Human behavior prediction is an interdisciplinary research direction, involving image processing, computer vision, pattern recognition, machine learning, and artificial intelligence, which is one of the important research topics in the field of computer vision. This paper introduces a model for predicting human skeletal motion sequence, which is composed of LSTM main network and structured prediction layer. We have verified its performance on h3.6m dataset, and this structure has achieved good results in the short-term prediction of human motion.

[1]  Geoffrey E. Hinton,et al.  Modeling Human Motion Using Binary Latent Variables , 2006, NIPS.

[2]  Cristian Sminchisescu,et al.  Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Francesc Moreno-Noguer,et al.  3D CNNs on Distance Matrices for Human Action Recognition , 2017, ACM Multimedia.

[4]  Silvio Savarese,et al.  Structural-RNN: Deep Learning on Spatio-Temporal Graphs , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Michael J. Black,et al.  On Human Motion Prediction Using Recurrent Neural Networks , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  José M. F. Moura,et al.  Adversarial Geometry-Aware Human Motion Prediction , 2018, ECCV.

[7]  Xu Chen,et al.  Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Jitendra Malik,et al.  Recurrent Network Models for Human Dynamics , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[9]  Dario Pavllo,et al.  QuaterNet: A Quaternion-based Recurrent Model for Human Motion , 2018, BMVC.