Semantic segmentation of motion capture sequences plays a key part in many data-driven motion synthesis frameworks. It is a preprocessing step in which long recordings of motion capture sequences are partitioned into smaller segments. Afterwards, additional methods like statistical modeling can be applied to each group of structurally-similar segments to learn an abstract motion manifold. The segmentation task however often remains a manual task, which increases the effort and cost of generating large-scale motion databases. We therefore propose an automatic framework for semantic segmentation of motion capture data using a dilated temporal fully-convolutional network. Our model outperforms a state-of-the-art model in action segmentation, as well as three networks for sequence modeling. We further show our model is robust against high noisy training labels.
@article{arxiv.1806.09174,
title = {Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data},
author = {Noshaba Cheema and Somayeh Hosseini and Janis Sprenger and Erik Herrmann and Han Du and Klaus Fischer and Philipp Slusallek},
journal= {arXiv preprint arXiv:1806.09174},
year = {2018}
}
Comments
Eurographics/ ACM SIGGRAPH Symposium on Computer Animation - Posters 2018; $\href{http://people.mpi-inf.mpg.de/~ncheema/SCA2018_poster.pdf}{\textit{Poster can be found here.}}$