Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Learning Motion Disfluencies for Automatic Sign Language Segmentation

Abstract: 

We introduce a novel technique for the automatic detection of word boundaries within continuous sentence expressions in Japanese Sign Language from three-dimensional body joint positions. First, the flow of signed sentence data within a temporal neighborhood is determined utilizing the spatial correlations between line segments of inter-joint pairs. Next, a frame-wise binary random forest classifier is trained to distinguish word and non-word frame content based on the extracted spatio-temporal features. The output of the classifier is used to propose an automatic word synthesis that achieves reliable and accurate sentence segmentation with an average frame-wise F1 score of 0.89. Evaluation with a baseline data set furthermore shows that the proposed approach can easily be adapted to distinguish between motion transitions and motion primitives for a coarse-action domain.

up
0 users have voted:

Paper Details

Authors:
Iva Farag
Submitted On:
9 May 2019 - 2:18am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Heike Brock
Paper Code:
4135
Document Year:
2019
Cite

Document Files

Poster.pdf

(179)

Subscribe

[1] Iva Farag, "Learning Motion Disfluencies for Automatic Sign Language Segmentation", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4154. Accessed: Sep. 19, 2020.
@article{4154-19,
url = {http://sigport.org/4154},
author = {Iva Farag },
publisher = {IEEE SigPort},
title = {Learning Motion Disfluencies for Automatic Sign Language Segmentation},
year = {2019} }
TY - EJOUR
T1 - Learning Motion Disfluencies for Automatic Sign Language Segmentation
AU - Iva Farag
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4154
ER -
Iva Farag. (2019). Learning Motion Disfluencies for Automatic Sign Language Segmentation. IEEE SigPort. http://sigport.org/4154
Iva Farag, 2019. Learning Motion Disfluencies for Automatic Sign Language Segmentation. Available at: http://sigport.org/4154.
Iva Farag. (2019). "Learning Motion Disfluencies for Automatic Sign Language Segmentation." Web.
1. Iva Farag. Learning Motion Disfluencies for Automatic Sign Language Segmentation [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4154