Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data

Noshaba Cheema, Somayeh Hosseini, Janis Sprenger, Erik Herrmann, Han Du, Klaus Fischer, Philipp Slusallek

In: Thabo Beeler, Nils Thuerey, Melina Skouras (editor). Eurographics/ ACM SIGGRAPH Symposium on Computer Animation - Posters. ACM SIGGRAPH / Eurographics Symposium on Computer Animation (SCA-2018) July 11-13 Paris France Pages 5-6 SCA Posters '18 ISBN 978-3-03868-070-3 The Eurographics Association 2018.


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.


DTFCN.pdf (pdf, 336 KB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz