Trajectorylet-Net: a novel framework for pose prediction based on trajectorylet descriptors
Preprint
Abstract
Pose prediction is an increasingly interesting topic in computer vision and robotics. In this paper, we propose a new network, Trajectorylet-Net, to predict future poses. Compared with most existing methods, our model focuses on modeling the co-occurrence long-term information and spatiotemporal correlation. Specifically, a novel descriptor, trajectorylet, is introduced to characterize the static and dynamic information of the input pose sequence. Then, a coupled spatio-temporal learning schema is proposed to generate trajectorylet descriptors, which can simultaneously capture the local structure of the human body and the global co-occurrence temporal information of the input sequence. Finally, we propose to predict future poses by gathering trajectorylet descriptors gradually. Extensive experiments show that our method achieves state-of-the-art performance on two benchmarks (e.g. G3D and FNTU), which demonstrates the effectiveness of our proposed method.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Modeling Human Motion with Quaternion-Based Neural NetworksInternational Journal of Computer Vision, 2019
- Towards Natural and Accurate Future Motion Prediction of Humans and Animals2019
- Efficient convolutional hierarchical autoencoder for human motion predictionThe Visual Computer, 2019
- Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification2018
- Few-Shot Human Motion Prediction via Meta-learning2018
- On Human Motion Prediction Using Recurrent Neural Networks2017
- Deep Representation Learning for Human Motion Prediction and Classification2017
- Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognitionPattern Recognition, 2017
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis2016
- Structural-RNN: Deep Learning on Spatio-Temporal Graphs2016