The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Nesta carta, propomos um novo método de regressão esparsa transferível (TSR), para reconhecimento de expressões faciais (FER) entre bancos de dados. No TSR, apresentamos primeiro uma nova função de regressão para regredir os dados para um espaço de representação latente em vez de um espaço de rótulo binário estrito. Para aliviar ainda mais a influência de outliers e overfitting, impomos uma restrição de esparsidade de linhas no termo de regressão. E um termo de relação de pares é introduzido para orientar o aprendizado de transferência de recursos. Em segundo lugar, projetamos um gráfico global para transferir conhecimento, que pode preservar a estrutura múltipla entre bancos de dados. Além disso, introduzimos uma restrição de baixa classificação no termo de regularização do gráfico para descobrir informações estruturais adicionais. Finalmente, vários experimentos são conduzidos em três bancos de dados populares de expressões faciais, e os resultados validam que o método TSR proposto é superior a outros métodos de aprendizagem por transferência profunda e não profunda.
Wenjing ZHANG
Yantai University
Peng SONG
Yantai University
Wenming ZHENG
Southeast University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Wenjing ZHANG, Peng SONG, Wenming ZHENG, "A Novel Transferable Sparse Regression Method for Cross-Database Facial Expression Recognition" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 1, pp. 184-188, January 2022, doi: 10.1587/transinf.2021EDL8062.
Abstract: In this letter, we propose a novel transferable sparse regression (TSR) method, for cross-database facial expression recognition (FER). In TSR, we firstly present a novel regression function to regress the data into a latent representation space instead of a strict binary label space. To further alleviate the influence of outliers and overfitting, we impose a row sparsity constraint on the regression term. And a pairwise relation term is introduced to guide the feature transfer learning. Secondly, we design a global graph to transfer knowledge, which can well preserve the cross-database manifold structure. Moreover, we introduce a low-rank constraint on the graph regularization term to uncover additional structural information. Finally, several experiments are conducted on three popular facial expression databases, and the results validate that the proposed TSR method is superior to other non-deep and deep transfer learning methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDL8062/_p
Copiar
@ARTICLE{e105-d_1_184,
author={Wenjing ZHANG, Peng SONG, Wenming ZHENG, },
journal={IEICE TRANSACTIONS on Information},
title={A Novel Transferable Sparse Regression Method for Cross-Database Facial Expression Recognition},
year={2022},
volume={E105-D},
number={1},
pages={184-188},
abstract={In this letter, we propose a novel transferable sparse regression (TSR) method, for cross-database facial expression recognition (FER). In TSR, we firstly present a novel regression function to regress the data into a latent representation space instead of a strict binary label space. To further alleviate the influence of outliers and overfitting, we impose a row sparsity constraint on the regression term. And a pairwise relation term is introduced to guide the feature transfer learning. Secondly, we design a global graph to transfer knowledge, which can well preserve the cross-database manifold structure. Moreover, we introduce a low-rank constraint on the graph regularization term to uncover additional structural information. Finally, several experiments are conducted on three popular facial expression databases, and the results validate that the proposed TSR method is superior to other non-deep and deep transfer learning methods.},
keywords={},
doi={10.1587/transinf.2021EDL8062},
ISSN={1745-1361},
month={January},}
Copiar
TY - JOUR
TI - A Novel Transferable Sparse Regression Method for Cross-Database Facial Expression Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 184
EP - 188
AU - Wenjing ZHANG
AU - Peng SONG
AU - Wenming ZHENG
PY - 2022
DO - 10.1587/transinf.2021EDL8062
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2022
AB - In this letter, we propose a novel transferable sparse regression (TSR) method, for cross-database facial expression recognition (FER). In TSR, we firstly present a novel regression function to regress the data into a latent representation space instead of a strict binary label space. To further alleviate the influence of outliers and overfitting, we impose a row sparsity constraint on the regression term. And a pairwise relation term is introduced to guide the feature transfer learning. Secondly, we design a global graph to transfer knowledge, which can well preserve the cross-database manifold structure. Moreover, we introduce a low-rank constraint on the graph regularization term to uncover additional structural information. Finally, several experiments are conducted on three popular facial expression databases, and the results validate that the proposed TSR method is superior to other non-deep and deep transfer learning methods.
ER -