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
미세 표현 인식(MER)은 미세 표현(ME)이 실제 감정을 추론할 수 있기 때문에 집중적인 연구 관심을 끌고 있습니다. 사전 정보는 모델이 차별적인 ME 기능을 효과적으로 학습하도록 안내할 수 있습니다. 그러나 대부분의 연구는 ME의 사전 정보와 속성을 무시할 수 있는 전체적인 방식으로 ME 이동 정보를 적응적으로 집계하는 더 강력한 표현 능력을 갖춘 일반 모델을 연구하는 데 중점을 둡니다. 이 문제를 해결하기 위해 ME의 범주가 얼굴의 다양한 구성 요소 동작 사이의 관계에 의해 추론될 수 있다는 사전 정보를 기반으로 이 작업은 이 사전 정보를 준수하고 해석 가능한 방식으로 ME 움직임 특징을 학습할 수 있는 새로운 모델을 설계합니다. 방법. 구체적으로 본 논문에서는 높은 수준의 ME 특성을 효과적으로 학습하기 위한 DeRe-GRL(Decomposition and Reconstruction-based Graph Representation Learning) 모델을 제안합니다. DeRe-GRL에는 ADM(Action Decomposition Module)과 RRM(Relation Reconstruction Module)이라는 두 가지 모듈이 포함되어 있습니다. 여기서 ADM은 안면 키 구성 요소의 동작 기능을 학습하고 RRM은 이러한 동작 기능 간의 관계를 탐색합니다. ADM은 얼굴 주요 구성 요소를 기반으로 그래프 모델 기반 백본에서 추출한 기하학적 움직임 특징을 여러 하위 특징으로 나누고 맵 매트릭스를 학습하여 이러한 하위 특징을 여러 동작 특징으로 매핑합니다. 그런 다음 RRM은 모든 작업 기능에 가중치를 부여하여 작업 기능 간의 관계를 구축하는 가중치를 학습합니다. 실험 결과는 제안된 모듈의 효율성을 입증했으며, 제안된 방법은 경쟁력 있는 성능을 달성했습니다.
Jinsheng WEI
Nanjing University of Posts and Telecommunications
Haoyu CHEN
Oulu of University
Guanming LU
Nanjing University of Posts and Telecommunications
Jingjie YAN
Nanjing University of Posts and Telecommunications
Yue XIE
Nanjing Institute of Technology
Guoying ZHAO
Oulu of 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.
부
Jinsheng WEI, Haoyu CHEN, Guanming LU, Jingjie YAN, Yue XIE, Guoying ZHAO, "Prior Information Based Decomposition and Reconstruction Learning for Micro-Expression Recognition" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 10, pp. 1752-1756, October 2023, doi: 10.1587/transinf.2022EDL8065.
Abstract: Micro-expression recognition (MER) draws intensive research interest as micro-expressions (MEs) can infer genuine emotions. Prior information can guide the model to learn discriminative ME features effectively. However, most works focus on researching the general models with a stronger representation ability to adaptively aggregate ME movement information in a holistic way, which may ignore the prior information and properties of MEs. To solve this issue, driven by the prior information that the category of ME can be inferred by the relationship between the actions of facial different components, this work designs a novel model that can conform to this prior information and learn ME movement features in an interpretable way. Specifically, this paper proposes a Decomposition and Reconstruction-based Graph Representation Learning (DeRe-GRL) model to efectively learn high-level ME features. DeRe-GRL includes two modules: Action Decomposition Module (ADM) and Relation Reconstruction Module (RRM), where ADM learns action features of facial key components and RRM explores the relationship between these action features. Based on facial key components, ADM divides the geometric movement features extracted by the graph model-based backbone into several sub-features, and learns the map matrix to map these sub-features into multiple action features; then, RRM learns weights to weight all action features to build the relationship between action features. The experimental results demonstrate the effectiveness of the proposed modules, and the proposed method achieves competitive performance.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDL8065/_p
부
@ARTICLE{e106-d_10_1752,
author={Jinsheng WEI, Haoyu CHEN, Guanming LU, Jingjie YAN, Yue XIE, Guoying ZHAO, },
journal={IEICE TRANSACTIONS on Information},
title={Prior Information Based Decomposition and Reconstruction Learning for Micro-Expression Recognition},
year={2023},
volume={E106-D},
number={10},
pages={1752-1756},
abstract={Micro-expression recognition (MER) draws intensive research interest as micro-expressions (MEs) can infer genuine emotions. Prior information can guide the model to learn discriminative ME features effectively. However, most works focus on researching the general models with a stronger representation ability to adaptively aggregate ME movement information in a holistic way, which may ignore the prior information and properties of MEs. To solve this issue, driven by the prior information that the category of ME can be inferred by the relationship between the actions of facial different components, this work designs a novel model that can conform to this prior information and learn ME movement features in an interpretable way. Specifically, this paper proposes a Decomposition and Reconstruction-based Graph Representation Learning (DeRe-GRL) model to efectively learn high-level ME features. DeRe-GRL includes two modules: Action Decomposition Module (ADM) and Relation Reconstruction Module (RRM), where ADM learns action features of facial key components and RRM explores the relationship between these action features. Based on facial key components, ADM divides the geometric movement features extracted by the graph model-based backbone into several sub-features, and learns the map matrix to map these sub-features into multiple action features; then, RRM learns weights to weight all action features to build the relationship between action features. The experimental results demonstrate the effectiveness of the proposed modules, and the proposed method achieves competitive performance.},
keywords={},
doi={10.1587/transinf.2022EDL8065},
ISSN={1745-1361},
month={October},}
부
TY - JOUR
TI - Prior Information Based Decomposition and Reconstruction Learning for Micro-Expression Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1752
EP - 1756
AU - Jinsheng WEI
AU - Haoyu CHEN
AU - Guanming LU
AU - Jingjie YAN
AU - Yue XIE
AU - Guoying ZHAO
PY - 2023
DO - 10.1587/transinf.2022EDL8065
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2023
AB - Micro-expression recognition (MER) draws intensive research interest as micro-expressions (MEs) can infer genuine emotions. Prior information can guide the model to learn discriminative ME features effectively. However, most works focus on researching the general models with a stronger representation ability to adaptively aggregate ME movement information in a holistic way, which may ignore the prior information and properties of MEs. To solve this issue, driven by the prior information that the category of ME can be inferred by the relationship between the actions of facial different components, this work designs a novel model that can conform to this prior information and learn ME movement features in an interpretable way. Specifically, this paper proposes a Decomposition and Reconstruction-based Graph Representation Learning (DeRe-GRL) model to efectively learn high-level ME features. DeRe-GRL includes two modules: Action Decomposition Module (ADM) and Relation Reconstruction Module (RRM), where ADM learns action features of facial key components and RRM explores the relationship between these action features. Based on facial key components, ADM divides the geometric movement features extracted by the graph model-based backbone into several sub-features, and learns the map matrix to map these sub-features into multiple action features; then, RRM learns weights to weight all action features to build the relationship between action features. The experimental results demonstrate the effectiveness of the proposed modules, and the proposed method achieves competitive performance.
ER -