Noshaba, CheemaHosseini, SomayehSprenger, JanisHerrmann, ErikDu, HanFischer, KlausSlusallek, PhilippSkouras, Melina2018-07-232018-07-232018978-3-03868-070-31727-5288https://doi.org/10.2312/sca.20181185https://diglib.eg.org:443/handle/10.2312/sca20181185Semantic 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.Computing methodologiesMotion processingMotion captureImage processing10.2312/sca.201811855-6