Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data
| dc.contributor.author | Noshaba, Cheema | en_US |
| dc.contributor.author | Hosseini, Somayeh | en_US |
| dc.contributor.author | Sprenger, Janis | en_US |
| dc.contributor.author | Herrmann, Erik | en_US |
| dc.contributor.author | Du, Han | en_US |
| dc.contributor.author | Fischer, Klaus | en_US |
| dc.contributor.author | Slusallek, Philipp | en_US |
| dc.contributor.editor | Skouras, Melina | en_US |
| dc.date.accessioned | 2018-07-23T10:10:16Z | |
| dc.date.available | 2018-07-23T10:10:16Z | |
| dc.date.issued | 2018 | |
| dc.description.abstract | 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. | en_US |
| dc.description.sectionheaders | Posters | |
| dc.description.seriesinformation | Eurographics/ ACM SIGGRAPH Symposium on Computer Animation - Posters | |
| dc.identifier.doi | 10.2312/sca.20181185 | |
| dc.identifier.isbn | 978-3-03868-070-3 | |
| dc.identifier.issn | 1727-5288 | |
| dc.identifier.pages | 5-6 | |
| dc.identifier.uri | https://doi.org/10.2312/sca.20181185 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/sca20181185 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.subject | Computing methodologies | |
| dc.subject | Motion processing | |
| dc.subject | Motion capture | |
| dc.subject | Image processing | |
| dc.title | Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data | en_US |