Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal Fully-Convolutional Networks
Loading...
Date
2019
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, naturallooking motions, most data-driven approaches require considerable efforts of pre-processing, including motion segmentation and annotation. Existing (semi-) automatic solutions either require hand-crafted features for motion segmentation or do not produce the semantic annotations required for motion synthesis and building large-scale motion databases. In addition, human labeled annotation data suffers from inter- and intra-labeler inconsistencies by design. We propose a semi-automatic framework for semantic segmentation of motion capture data based on supervised machine learning techniques. It first transforms a motion capture sequence into a ''motion image'' and applies a convolutional neural network for image segmentation. Dilated temporal convolutions enable the extraction of temporal information from a large receptive field. Our model outperforms two state-of-the-art models for action segmentation, as well as a popular network for sequence modeling. Most of all, our method is very robust under noisy and inaccurate training labels and thus can handle human errors during the labeling process.
Description
@inproceedings{10.2312:egs.20191017,
booktitle = {Eurographics 2019 - Short Papers},
editor = {Cignoni, Paolo and Miguel, Eder},
title = {{Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal Fully-Convolutional Networks}},
author = {Cheema, Noshaba and hosseini, somayeh and Sprenger, Janis and Herrmann, Erik and Du, Han and Fischer, Klaus and Slusallek, Philipp},
year = {2019},
publisher = {The Eurographics Association},
ISSN = {1017-4656},
ISBN = {},
DOI = {10.2312/egs.20191017}
}