Manifold feature integration for micro-expression recognition

Takalkar, Madhumita A.; Xu, Min; Chaczko, Zenon

doi:10.1007/s00530-020-00663-8

“…The dimensional emotion description model, also known as the continuous emotion description model, describes specific emotion attributes as coordinates in a spatial dimension. Each axis corresponds to a particular attribute of emotion [ 26 ]. Existing theories of specific emotional states can have corresponding coordinates in emotion space, with the values on each axis indicating the intensity of the corresponding attribute.…”

Section: Design Of Classroom Emotion Recognition Model Based On Convo...mentioning

confidence: 99%

A Classroom Emotion Recognition Model Based on a Convolutional Neural Network Speech Emotion Algorithm

Yuan

¹

2022

Occupational Therapy International

View full text Add to dashboard Cite

In this paper, we construct a model of convolutional neural network speech emotion algorithm, analyze the classroom identified by the neural network with a certain degree of confidence together with the school used in the dataset, find the characteristics and rules of teachers’ control of classroom emotion nowadays using big data, find the parts of classroom emotion, and design a classroom emotion recognition model based on convolutional neural network speech emotion algorithm according to these characteristics. This paper will investigate the factors and patterns of teachers’ emotional control in the classroom. In this paper, the existing neural network is adapted and improved, and some preprocessing is performed on the current dataset to train the network. The network used in this paper is a combination of convolutional neural network (CNN) and recurrent neural network (RNN), which takes advantage of both CNN for feature extraction and RNN for memory capability in the sequence model. This network has a good effect on both object labeling and speech recognition. For the problem of extracting emotion features of whole-sentence speech, we propose an attention mechanism-based emotion recognition algorithm for variable-length speech and design a spatiotemporal attention module for the speech emotion algorithm and a convolutional channel attention module for the CNN network to reduce the contribution of the spatiotemporal data of the speech emotion algorithm and the unimportant parts of the CNN convolutional channel feature data in the subsequent recognition by the attention mechanism. In turn, the weight of core key data and features is increased to improve the model recognition accuracy.

show abstract

“…Ranking Loss, such as Contrastive Loss, Margin Loss, Hinge Loss or Triplet Loss, is widely used in MER [70], [160], [136], [55], [161], [162], [71], [163]. The objective of ranking loss is to predict relative distances between inputs, which is also called metric learning [164].…”

Section: Ranking Lossmentioning

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

“…Ranking Loss, such as Contrastive Loss, Margin Loss, Hinge Loss or Triplet Loss, is widely used in MER [82], [173], [153], [60], [174], [175], [83], [176]. The objective of ranking loss is to predict relative distances between inputs, which is also called metric learning [177].…”

Section: Ranking Lossmentioning

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

Manifold feature integration for micro-expression recognition

Cited by 31 publications

References 48 publications

A Classroom Emotion Recognition Model Based on a Convolutional Neural Network Speech Emotion Algorithm

A Classroom Emotion Recognition Model Based on a Convolutional Neural Network Speech Emotion Algorithm

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

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

Contact Info

Product

Resources

About