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

06/24/2018
by   Noshaba Cheema, et al.
0

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.

READ FULL TEXT
research
03/02/2019

Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal Fully-Convolutional Networks

Human motion capture data has been widely used in data-driven character ...
research
11/16/2016

Convolutional Gated Recurrent Networks for Video Segmentation

Semantic segmentation has recently witnessed major progress, where fully...
research
09/20/2019

Weakly Supervised Semantic Segmentation Using Constrained Dominant Sets

The availability of large-scale data sets is an essential pre-requisite ...
research
02/07/2022

PSSNet: Planarity-sensible Semantic Segmentation of Large-scale Urban Meshes

We introduce a novel deep learning-based framework to interpret 3D urban...
research
06/30/2018

Quantity beats quality for semantic segmentation of corrosion in images

Dataset creation is typically one of the first steps when applying Artif...
research
12/13/2015

Unsupervised Temporal Segmentation of Repetitive Human Actions Based on Kinematic Modeling and Frequency Analysis

In this paper, we propose a method for temporal segmentation of human re...
research
06/09/2018

Fully Convolutional Networks with Sequential Information for Robust Crop and Weed Detection in Precision Farming

Reducing the use of agrochemicals is an important component towards sust...

Please sign up or login with your details

Forgot password? Click here to reset