Multiple source domain adaptation in micro-expression recognition

Zhang, Xiaorui; Tian, Xu; Sun, Wei; Song, Aiguo

doi:10.1007/s12652-020-02569-9

“…Cross-dataset MER is one of the recently emerging while challenging problems in ME analysis. The training sets and testing sets are from different ME datasets, resulting in the inconsistency of feature distributions [172].…”

Section: Cross-dataset Mermentioning

confidence: 99%

“…The idea is that such coefficient matrix could also reflect the sample-label relation in the target database domain. Zhang et al [172] proposed a structure of the super wide regression network (SWiRN) for unsupervised cross-database MER. The state-of-the-art domain adaptation methods [174], [175] can be further exploited to reduce the differences between source and target domains to improve the performance of CDMER methods.…”

Section: Cross-dataset Mermentioning

confidence: 99%

An Overview of Facial Micro-Expression Analysis: Data, Methodology and Challenge

Xie¹,

Lo²,

Shuai³

et al. 2023

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

Facial micro-expressions indicate brief and subtle facial movements that appear during emotional communication. In comparison to macro-expressions, micro-expressions are more challenging to be analyzed due to the short span of time and the fine-grained changes. In recent years, micro-expression recognition (MER) has drawn much attention because it can benefit a wide range of applications, e.g. police interrogation, clinical diagnosis, depression analysis, and business negotiation. In this survey, we offer a fresh overview to discuss new research directions and challenges these days for MER tasks. For example, we review MER approaches from three novel aspects: macro-to-micro adaptation, recognition based on key apex frames, and recognition based on facial action units. Moreover, to mitigate the problem of limited and biased ME data, synthetic data generation is surveyed for the diversity enrichment of micro-expression data. Since micro-expression spotting can boost micro-expression analysis, the state-of-the-art spotting works are also introduced in this paper. At last, we discuss the challenges in MER research and provide potential solutions as well as possible directions for further investigation.

show abstract

“…Cross-dataset MER is one of the recently emerging while challenging problems in ME analysis. The training sets and testing sets are from different ME datasets, resulting in the inconsistency of feature distributions [185].…”

Section: Cross-dataset Mermentioning

confidence: 99%

“…The idea is that such coefficient matrix could also reflect the sample-label relation in the target database domain. Zhang et al [185] proposed a structure of the super wide regression network (SWiRN) for unsupervised cross-database MER. The state-of-the-art domain adaptation methods [187], [188] can be further exploited to reduce the differences between source and target domains to improve the performance of CDMER methods.…”

Section: Cross-dataset Mermentioning

confidence: 99%

An Overview of Facial Micro-Expression Analysis: Data, Methodology and Challenge

Xie¹,

Lo²,

Shuai³

et al. 2020

Preprint

View full text Add to dashboard Cite

Facial micro-expressions indicate brief and subtle facial movements that appear during emotional communication. In comparison to macro-expressions, micro-expressions are more challenging to be analyzed due to the short span of time and the fine-grained changes. In recent years, micro-expression recognition (MER) has drawn much attention because it can benefit a wide range of applications, e.g. police interrogation, clinical diagnosis, depression analysis, and business negotiation. In this survey, we offer a fresh overview to discuss new research directions and challenges these days for MER tasks. For example, we review MER approaches from three novel aspects: macro-to-micro adaptation, recognition based on key apex frames, and recognition based on facial action units. Moreover, to mitigate the problem of limited and biased ME data, synthetic data generation is surveyed for the diversity enrichment of micro-expression data. Since micro-expression spotting can boost micro-expression analysis, the state-of-the-art spotting works are also introduced in this paper. At last, we discuss the challenges in MER research and provide potential solutions as well as possible directions for further investigation.

show abstract

“…Emotional interaction with the intelligent companion robot can effectively relieve their negative emotions [1,2]. There are many ways to obtain emotional information in human-computer interaction [3][4][5]. Former researches show that people of different cultures have the same facial expressions to express their negative emotions [6].…”

Section: Introductionmentioning

confidence: 99%

Negative Emotions Sensitive Humanoid Robot with Attention-Enhanced Facial Expression Recognition Network

Ni¹,

Liu²,

Zhou³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Lonely older adults and persons restricted in movements are apt to cause negative emotions, which is harmful to their mental health. A humanoid robot with audiovisual interactions is presented, which can correspondingly output positive facial expressions to relieve human's negative facial expressions. The negative emotions are identified through an attention-enhanced facial expression recognition (FER) network. The network is firstly trained on MMEW macro-and micro-expression databases to discover expression-related features. Then, macroexpression recognition tasks are performed by fine-tuning the trained models on several benchmarking FER databases, including CK+ and Oulu-CASIA. A transformer network is introduced to process the sequential features engineered by the FER network and output a final stable control order. This order is used to control the robot's facial motor units to generate different expressions, e.g., a smile expression. Evaluations on benchmarking databases verify that the proposed method can precisely recognize facial expressions. The joint modulation with the humanoid robot proves that the robot can respond effectively to the user's negative emotions.

show abstract

Multiple source domain adaptation in micro-expression recognition

Cited by 10 publications

References 36 publications

An Overview of Facial Micro-Expression Analysis: Data, Methodology and Challenge

An Overview of Facial Micro-Expression Analysis: Data, Methodology and Challenge

An Overview of Facial Micro-Expression Analysis: Data, Methodology and Challenge

Negative Emotions Sensitive Humanoid Robot with Attention-Enhanced Facial Expression Recognition Network

Contact Info

Product

Resources

About