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

facebooktwittermailshare

Key Action And Joint CTC-Attention Based Sign Language Recognition

Abstract: 

Sign Language Recognition (SLR) translates sign language video into natural language. In practice, sign language video, owning a large number of redundant frames, is necessary to be selected the essential. However, unlike common video that describes actions, sign language video is characterized as continuous and dense action sequence, which is difficult to capture key actions corresponding to meaningful sentence. In this paper, we propose to hierarchically search key actions by a pyramid BiLSTM. Specifically, we first construct three BiLSTMs to produce temporal relationships among input video sequence. Then, we associate these BiLSTMs by searching the salient responses in two groups of fixed-scale sliding window and capture key actions. Additionally, in order to balance the sequence alignment and dependency, we propose to jointly train Connectionist Temporal Classification (CTC) and Long Short-Term Memory (LSTM). Experimental results demonstrate the effectiveness of the proposed method

up
0 users have voted:

Paper Details

Authors:
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng
Submitted On:
16 April 2020 - 11:39am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Liqing Gao
Paper Code:
ICASSP-5717
Document Year:
2020
Cite

Document Files

poster_video5717.pdf

(62)

Subscribe

[1] Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng, "Key Action And Joint CTC-Attention Based Sign Language Recognition", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5100. Accessed: Oct. 24, 2020.
@article{5100-20,
url = {http://sigport.org/5100},
author = {Haibo Li; Liqing Gao; Ruize Han; Liang Wan; Wei Feng },
publisher = {IEEE SigPort},
title = {Key Action And Joint CTC-Attention Based Sign Language Recognition},
year = {2020} }
TY - EJOUR
T1 - Key Action And Joint CTC-Attention Based Sign Language Recognition
AU - Haibo Li; Liqing Gao; Ruize Han; Liang Wan; Wei Feng
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5100
ER -
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. (2020). Key Action And Joint CTC-Attention Based Sign Language Recognition. IEEE SigPort. http://sigport.org/5100
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng, 2020. Key Action And Joint CTC-Attention Based Sign Language Recognition. Available at: http://sigport.org/5100.
Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. (2020). "Key Action And Joint CTC-Attention Based Sign Language Recognition." Web.
1. Haibo Li, Liqing Gao, Ruize Han, Liang Wan, Wei Feng. Key Action And Joint CTC-Attention Based Sign Language Recognition [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5100