Although significant progress has been made in micro-expression recognition,effectively modeling the intricate spatial-temporal dynamics remains a persistent challenge owing to their brief duration and complex facial ...Although significant progress has been made in micro-expression recognition,effectively modeling the intricate spatial-temporal dynamics remains a persistent challenge owing to their brief duration and complex facial dynamics.Furthermore,existing methods often suffer from limited gen-eralization,as they primarily focus on single-dataset tasks with small sample sizes.To address these two issues,this paper proposes the cross-domain spatial-temporal graph convolutional network(GCN)(CDST-GCN)model,which comprises two primary components:a siamese attention spa-tial-temporal branch(SASTB)and a global-aware dynamic spatial-temporal branch(GDSTB).Specifically,SASTB utilizes a contrastive learning strategy to project macro-and micro-expressions into a shared,aligned feature space,actively addressing cross-domain discrepancies.Additionally,it integrates an attention-gated mechanism that generates adaptive adjacency matrices to flexibly model collaborative patterns among facial landmarks.While largely preserving the structural paradigm of SASTB,GDSTB enhances the feature representation by integrating global context extracted from a pretrained model.Through this dual-branch architecture,CDST-GCN success-fully models both the global and local spatial-temporal features.The experimental results on CASME II and SAMM datasets demonstrate that the proposed model achieves competitive perfor-mance.Especially in more challenging 5-class tasks,the accuracy of the model on CASME II dataset is as high as 80.5%.展开更多
The lack of facial features caused by wearing masks degrades the performance of facial recognition systems.Traditional occluded face recognition methods cannot integrate the computational resources of the edge layer a...The lack of facial features caused by wearing masks degrades the performance of facial recognition systems.Traditional occluded face recognition methods cannot integrate the computational resources of the edge layer and the device layer.Besides,previous research fails to consider the facial characteristics including occluded and unoccluded parts.To solve the above problems,we put forward a device-edge collaborative occluded face recognition method based on cross-domain feature fusion.Specifically,the device-edge collaborative face recognition architecture gets the utmost out of maximizes device and edge resources for real-time occluded face recognition.Then,a cross-domain facial feature fusion method is presented which combines both the explicit domain and the implicit domain facial.Furthermore,a delay-optimized edge recognition task scheduling method is developed that comprehensively considers the task load,computational power,bandwidth,and delay tolerance constraints of the edge.This method can dynamically schedule face recognition tasks and minimize recognition delay while ensuring recognition accuracy.The experimental results show that the proposed method achieves an average gain of about 21%in recognition latency,while the accuracy of the face recognition task is basically the same compared to the baseline method.展开更多
Micro-expressions are spontaneous, unconscious movements that reveal true emotions.Accurate facial movement information and network training learning methods are crucial for micro-expression recognition.However, most ...Micro-expressions are spontaneous, unconscious movements that reveal true emotions.Accurate facial movement information and network training learning methods are crucial for micro-expression recognition.However, most existing micro-expression recognition technologies so far focus on modeling the single category of micro-expression images and neural network structure.Aiming at the problems of low recognition rate and weak model generalization ability in micro-expression recognition, a micro-expression recognition algorithm is proposed based on graph convolution network(GCN) and Transformer model.Firstly, action unit(AU) feature detection is extracted and facial muscle nodes in the neighborhood are divided into three subsets for recognition.Then, graph convolution layer is used to find the layout of dependencies between AU nodes of micro-expression classification.Finally, multiple attentional features of each facial action are enriched with Transformer model to include more sequence information before calculating the overall correlation of each region.The proposed method is validated in CASME II and CAS(ME)^2 datasets, and the recognition rate reached 69.85%.展开更多
Facial micro-expressions are short and imperceptible expressions that involuntarily reveal the true emotions that a person may be attempting to suppress,hide,disguise,or conceal.Such expressions can reflect a person&#...Facial micro-expressions are short and imperceptible expressions that involuntarily reveal the true emotions that a person may be attempting to suppress,hide,disguise,or conceal.Such expressions can reflect a person's real emotions and have a wide range of application in public safety and clinical diagnosis.The analysis of facial micro-expressions in video sequences through computer vision is still relatively recent.In this research,a comprehensive review on the topic of spotting and recognition used in micro expression analysis databases and methods,is conducted,and advanced technologies in this area are summarized.In addition,we discuss challenges that remain unresolved alongside future work to be completed in the field of micro-expression analysis.展开更多
Micro-expression recognition has attracted growing research interests in the field of compute vision.However,micro-expression usually lasts a few seconds,thus it is difficult to detect.This paper presents a new framew...Micro-expression recognition has attracted growing research interests in the field of compute vision.However,micro-expression usually lasts a few seconds,thus it is difficult to detect.This paper presents a new framework to recognize micro-expression using pyramid histogram of Centralized Gabor Binary Pattern from Three Orthogonal Panels(CGBP-TOP)which is an extension of Local Gabor Binary Pattern from Three Orthogonal Panels feature.CGBP-TOP performs spatial and temporal analysis to capture the local facial characteristics of micro-expression image sequences.In order to keep more local information of the face,CGBP-TOP is extracted based on pyramid subregions of the micro-expression video frame.The combination of CGBP-TOP and spatial pyramid can represent well and truly the facial movements of the micro-expression image sequences.However,the dimension of our pyramid CGBP-TOP tends to be very high,which may lead to high data redundancy problem.In addition,it is clear that people of different genders usually have different ways of micro-expression.Therefore,in this paper,in order to select the relevant features of micro-expression,the gender-specific sparse multi-task learning method with adaptive regularization term is adopted to learn a compact subset of pyramid CGBP-TOP feature for micro-expression classification of different sexes.Finally,extensive experiments on widely used CASME II and SMIC databases demonstrate that our method can efficiently extract micro-expression motion features in the micro-expression video clip.Moreover,our proposed approach achieves comparable results with the state-of-the-art methods.展开更多
Aiming at the problems of short duration,low intensity,and difficult detection of micro-expressions(MEs),the global and local features of ME video frames are extracted by combining spatial feature extraction and tempo...Aiming at the problems of short duration,low intensity,and difficult detection of micro-expressions(MEs),the global and local features of ME video frames are extracted by combining spatial feature extraction and temporal feature extraction.Based on traditional convolution neural network(CNN)and long short-term memory(LSTM),a recognition method combining global identification attention network(GIA),block identification attention network(BIA)and bi-directional long short-term memory(Bi-LSTM)is proposed.In the BIA,the ME video frame will be cropped,and the training will be carried out by cropping into 24 identification blocks(IBs),10 IBs and uncropped IBs.To alleviate the overfitting problem in training,we first extract the basic features of the preprocessed sequence through the transfer learning layer,and then extract the global and local spatial features of the output data through the GIA layer and the BIA layer,respectively.In the BIA layer,the input data will be cropped into local feature vectors with attention weights to extract the local features of the ME frames;in the GIA layer,the global features of the ME frames will be extracted.Finally,after fusing the global and local feature vectors,the ME time-series information is extracted by Bi-LSTM.The experimental results show that using IBs can significantly improve the model’s ability to extract subtle facial features,and the model works best when 10 IBs are used.展开更多
Aiming at the problem of unsatisfactory effects of traditional micro-expression recognition algorithms,an efficient micro-expression recognition algorithm is proposed,which uses convolutional neural networks(CNN)to ex...Aiming at the problem of unsatisfactory effects of traditional micro-expression recognition algorithms,an efficient micro-expression recognition algorithm is proposed,which uses convolutional neural networks(CNN)to extract spatial features of micro-expressions,and long short-term memory network(LSTM)to extract time domain features.CNN and LSTM are combined as the basis of micro-expression recognition.In many CNN structures,the visual geometry group(VGG)using a small convolution kernel is finally selected as the pre-network through comparison.Due to the difficulty of deep learning training and over-fitting,the dropout method and batch normalization method are used to solve the problem in the VGG network.Two data sets CASME and CASME II are used for test comparison,in order to solve the problem of insufficient data sets,randomly determine the starting frame,and a fixedlength frame sequence is used as the standard,and repeatedly read all sample frames of the entire data set to achieve trayersal and data amplification.Finallv.a hieh recognition rate of 67.48% is achieved.展开更多
The intensity of the micro-expression is weak,although the directional low frequency components in the image are preserved by many algorithms,the extracted micro-expression ft^ature information is not sufficient to ac...The intensity of the micro-expression is weak,although the directional low frequency components in the image are preserved by many algorithms,the extracted micro-expression ft^ature information is not sufficient to accurately represent its sequences.In order to improve the accuracy of micro-expression recognition,first,each frame image is extracted from,its sequences,and the image frame is pre-processed by using gray normalization,size normalization,and two-dimensional principal component analysis(2DPCA);then,the optical flow method is used to extract the motion characteristics of the reduced-dimensional image,the information entropy value of the optical flow characteristic image is calculated by the information entropy principle,and the information entropy value is analyzed to obtain the eigenvalue.Therefore,more micro-expression feature information is extracted,including more important information,which can further improve the accuracy of micro-expression classification and recognition;finally,the feature images are classified by using the support vector machine(SVM).The experimental results show that the micro-expression feature image obtained by the information entropy statistics can effectively improve the accuracy of micro-expression recognition.展开更多
The micro-expression lasts for a very short time and the intensity is very subtle.Aiming at the problem of its low recognition rate,this paper proposes a new micro-expression recognition algorithm based on a three-dim...The micro-expression lasts for a very short time and the intensity is very subtle.Aiming at the problem of its low recognition rate,this paper proposes a new micro-expression recognition algorithm based on a three-dimensional convolutional neural network(3D-CNN),which can extract two-di-mensional features in spatial domain and one-dimensional features in time domain,simultaneously.The network structure design is based on the deep learning framework Keras,and the discarding method and batch normalization(BN)algorithm are effectively combined with three-dimensional vis-ual geometry group block(3D-VGG-Block)to reduce the risk of overfitting while improving training speed.Aiming at the problem of the lack of samples in the data set,two methods of image flipping and small amplitude flipping are used for data amplification.Finally,the recognition rate on the data set is as high as 69.11%.Compared with the current international average micro-expression recog-nition rate of about 67%,the proposed algorithm has obvious advantages in recognition rate.展开更多
Background The use of micro-expression recognition to recognize human emotions is one of the most critical challenges in human-computer interaction applications. In recent years, cross-database micro-expression recogn...Background The use of micro-expression recognition to recognize human emotions is one of the most critical challenges in human-computer interaction applications. In recent years, cross-database micro-expression recognition(CDMER) has emerged as a significant challenge in micro-expression recognition and analysis. Because the training and testing data in CDMER come from different micro-expression databases, CDMER is more challenging than conventional micro-expression recognition. Methods In this paper, an adaptive spatio-temporal attention neural network(ASTANN) using an attention mechanism is presented to address this challenge. To this end, the micro-expression databases SMIC and CASME II are first preprocessed using an optical flow approach,which extracts motion information among video frames that represent discriminative features of micro-expression.After preprocessing, a novel adaptive framework with a spatiotemporal attention module was designed to assign spatial and temporal weights to enhance the most discriminative features. The deep neural network then extracts the cross-domain feature, in which the second-order statistics of the sample features in the source domain are aligned with those in the target domain by minimizing the correlation alignment(CORAL) loss such that the source and target databases share similar distributions. Results To evaluate the performance of ASTANN, experiments were conducted based on the SMIC and CASME II databases under the standard experimental evaluation protocol of CDMER. The experimental results demonstrate that ASTANN outperformed other methods in relevant crossdatabase tasks. Conclusions Extensive experiments were conducted on benchmark tasks, and the results show that ASTANN has superior performance compared with other approaches. This demonstrates the superiority of our method in solving the CDMER problem.展开更多
Biometric recognition refers to the process of recognizing a person’s identity using physiological or behavioral modalities,such as face,voice,fingerprint,gait,etc.Such biometric modalities are mostly used in recogni...Biometric recognition refers to the process of recognizing a person’s identity using physiological or behavioral modalities,such as face,voice,fingerprint,gait,etc.Such biometric modalities are mostly used in recognition tasks separately as in unimodal systems,or jointly with two or more as in multimodal systems.However,multimodal systems can usually enhance the recognition performance over unimodal systems by integrating the biometric data of multiple modalities at different fusion levels.Despite this enhancement,in real-life applications some factors degrade multimodal systems’performance,such as occlusion,face poses,and noise in voice data.In this paper,we propose two algorithms that effectively apply dynamic fusion at feature level based on the data quality of multimodal biometrics.The proposed algorithms attempt to minimize the negative influence of confusing and low-quality features by either exclusion or weight reduction to achieve better recognition performance.The proposed dynamic fusion was achieved using face and voice biometrics,where face features were extracted using principal component analysis(PCA),and Gabor filters separately,whilst voice features were extracted using Mel-Frequency Cepstral Coefficients(MFCCs).Here,the facial data quality assessment of face images is mainly based on the existence of occlusion,whereas the assessment of voice data quality is substantially based on the calculation of signal to noise ratio(SNR)as per the existence of noise.To evaluate the performance of the proposed algorithms,several experiments were conducted using two combinations of three different databases,AR database,and the extended Yale Face Database B for face images,in addition to VOiCES database for voice data.The obtained results show that both proposed dynamic fusion algorithms attain improved performance and offer more advantages in identification and verification over not only the standard unimodal algorithms but also the multimodal algorithms using standard fusion methods.展开更多
Micro-Expression Recognition(MER)is a challenging task as the subtle changes occur over different action regions of a face.Changes in facial action regions are formed as Action Units(AUs),and AUs in micro-expressions ...Micro-Expression Recognition(MER)is a challenging task as the subtle changes occur over different action regions of a face.Changes in facial action regions are formed as Action Units(AUs),and AUs in micro-expressions can be seen as the actors in cooperative group activities.In this paper,we propose a novel deep neural network model for objective class-based MER,which simultaneously detects AUs and aggregates AU-level features into micro-expression-level representation through Graph Convolutional Networks(GCN).Specifically,we propose two new strategies in our AU detection module for more effective AU feature learning:the attention mechanism and the balanced detection loss function.With these two strategies,features are learned for all the AUs in a unified model,eliminating the error-prune landmark detection process and tedious separate training for each AU.Moreover,our model incorporates a tailored objective class-based AU knowledge-graph,which facilitates the GCN to aggregate the AU-level features into a micro-expression-level feature representation.Extensive experiments on two tasks in MEGC 2018 show that our approach outperforms the current state-of-the-art methods in MER.Additionally,we also report our single model-based micro-expression AU detection results.展开更多
As mobile devices and sensor technology advance,their role in communication becomes increasingly indispensable.Micro-expression recognition,an invaluable non-verbal communication method,has been extensively studied in...As mobile devices and sensor technology advance,their role in communication becomes increasingly indispensable.Micro-expression recognition,an invaluable non-verbal communication method,has been extensively studied in human-computer interaction,sentiment analysis,and security fields.However,the sensitivity and privacy implications of micro-expression data pose significant challenges for centralized machine learning methods,raising concerns about serious privacy leakage and data sharing.To address these limitations,we investigate a federated learning scheme tailored specifically for this task.Our approach prioritizes user privacy by employing federated optimization techniques,enabling the aggregation of clients’knowledge in an encrypted space without compromising data privacy.By integrating established micro-expression recognition methods into our framework,we demonstrate that our approach not only ensures robust data protection but also maintains high recognition performance comparable to non-privacy-preserving mechanisms.To our knowledge,this marks the first application of federated learning to the micro-expression recognition task.展开更多
Micro-expression recognition is a substantive cross-study of psychology and computer science,and it has a wide range of applications(e.g.,psychological and clinical diagnosis,emotional analysis,criminal investigation,...Micro-expression recognition is a substantive cross-study of psychology and computer science,and it has a wide range of applications(e.g.,psychological and clinical diagnosis,emotional analysis,criminal investigation,etc.).However,the subtle and diverse changes in facial muscles make it difficult for existing methods to extract effective features,which limits the improvement of micro-expression recognition accuracy.Therefore,we propose a multi-scale joint feature network based on optical flow images for micro-expression recognition.First,we generate an optical flow image that reflects subtle facial motion information.The optical flow image is then fed into the multi-scale joint network for feature extraction and classification.The proposed joint feature module(JFM)integrates features from different layers,which is beneficial for the capture of micro-expression features with different amplitudes.To improve the recognition ability of the model,we also adopt a strategy for fusing the feature prediction results of the three JFMs with the backbone network.Our experimental results show that our method is superior to state-of-the-art methods on three benchmark datasets(SMIC,CASME II,and SAMM)and a combined dataset(3 DB).展开更多
Micro-expressions are spontaneous,rapid and subtle facial movements that can hardly be suppressed or fabricated.Micro-expression recognition(MER)is one of the most challenging topics in affective computing.It aims to ...Micro-expressions are spontaneous,rapid and subtle facial movements that can hardly be suppressed or fabricated.Micro-expression recognition(MER)is one of the most challenging topics in affective computing.It aims to recognize subtle facial movements which are quite difficult for humans to perceive in a fleeting period.Recently,many deep learning-based MER methods have been developed.However,how to effectively capture subtle temporal variations for robust MER still perplexes us.We propose a counterfactual discriminative micro-expression recognition(CoDER)method to effectively learn the slight temporal variations for video-based MER.To explicitly capture the causality from temporal dynamics hidden in the micro-expression(ME)sequence,we propose ME counterfactual reasoning by comparing the effects of the facts w.r.t.original ME sequences and the counterfactuals w.r.t.counterfactually-revised ME sequences,and then perform causality-aware prediction to encourage the model to learn those latent ME temporal cues.Extensive experiments on four widely-used ME databases demonstrate the effectiveness of CoDER,which results in comparable and superior MER performance compared with that of the state-of-the-art methods.The visualization results show that CoDER successfully perceives the meaningful temporal variations in sequential faces.展开更多
基金funded in part by the National Natural Science Foundation of China(Nos.62322111,62271289,62501186)the Natural Science Fund for Outstanding Young Scholars of Shandong Province(No.ZR2022YQ60)+4 种基金the Research Fund for the Taishan Scholar Project of Shandong Province(No.tsqn202306064)the Natural Science Fund for Distinguished Young Scientists of ShandongProvince(No.ZR2024JQ007)Shenzhen Science and Technology Program(No.JCYJ20240813101228036)Jinan“20 Terms of New Universities”Funding Project(No.202333035)the Fundamental Research funds for theCentral Universities(No.3072025CFJ0805).
文摘Although significant progress has been made in micro-expression recognition,effectively modeling the intricate spatial-temporal dynamics remains a persistent challenge owing to their brief duration and complex facial dynamics.Furthermore,existing methods often suffer from limited gen-eralization,as they primarily focus on single-dataset tasks with small sample sizes.To address these two issues,this paper proposes the cross-domain spatial-temporal graph convolutional network(GCN)(CDST-GCN)model,which comprises two primary components:a siamese attention spa-tial-temporal branch(SASTB)and a global-aware dynamic spatial-temporal branch(GDSTB).Specifically,SASTB utilizes a contrastive learning strategy to project macro-and micro-expressions into a shared,aligned feature space,actively addressing cross-domain discrepancies.Additionally,it integrates an attention-gated mechanism that generates adaptive adjacency matrices to flexibly model collaborative patterns among facial landmarks.While largely preserving the structural paradigm of SASTB,GDSTB enhances the feature representation by integrating global context extracted from a pretrained model.Through this dual-branch architecture,CDST-GCN success-fully models both the global and local spatial-temporal features.The experimental results on CASME II and SAMM datasets demonstrate that the proposed model achieves competitive perfor-mance.Especially in more challenging 5-class tasks,the accuracy of the model on CASME II dataset is as high as 80.5%.
基金supported by National Natural Science Foundation of China(61901071,61871062,61771082,U20A20157)Science and Natural Science Foundation of Chongqing,China(cstc2020jcyjzdxmX0024)+6 种基金University Innovation Research Group of Chongqing(CXQT20017)Program for Innovation Team Building at Institutions of Higher Education in Chongqing(CXTDX201601020)Natural Science Foundation of Chongqing,China(CSTB2022NSCQ-MSX0600)Youth Innovation Group Support Program of ICE Discipline of CQUPT(SCIE-QN-2022-04)Chongqing Municipal Technology Innovation and Application Development Special Key Project(cstc2020jscxdxwtBX0053)China Postdoctoral Science Foundation Project,China(2022MD723723)Chongqing Postdoctoral Research Project Special Funding,China(2023CQBSHTB3092)。
文摘The lack of facial features caused by wearing masks degrades the performance of facial recognition systems.Traditional occluded face recognition methods cannot integrate the computational resources of the edge layer and the device layer.Besides,previous research fails to consider the facial characteristics including occluded and unoccluded parts.To solve the above problems,we put forward a device-edge collaborative occluded face recognition method based on cross-domain feature fusion.Specifically,the device-edge collaborative face recognition architecture gets the utmost out of maximizes device and edge resources for real-time occluded face recognition.Then,a cross-domain facial feature fusion method is presented which combines both the explicit domain and the implicit domain facial.Furthermore,a delay-optimized edge recognition task scheduling method is developed that comprehensively considers the task load,computational power,bandwidth,and delay tolerance constraints of the edge.This method can dynamically schedule face recognition tasks and minimize recognition delay while ensuring recognition accuracy.The experimental results show that the proposed method achieves an average gain of about 21%in recognition latency,while the accuracy of the face recognition task is basically the same compared to the baseline method.
基金Supported by Shaanxi Province Key Research and Development Project (2021GY-280)the National Natural Science Foundation of China (No.61834005,61772417,61802304)。
文摘Micro-expressions are spontaneous, unconscious movements that reveal true emotions.Accurate facial movement information and network training learning methods are crucial for micro-expression recognition.However, most existing micro-expression recognition technologies so far focus on modeling the single category of micro-expression images and neural network structure.Aiming at the problems of low recognition rate and weak model generalization ability in micro-expression recognition, a micro-expression recognition algorithm is proposed based on graph convolution network(GCN) and Transformer model.Firstly, action unit(AU) feature detection is extracted and facial muscle nodes in the neighborhood are divided into three subsets for recognition.Then, graph convolution layer is used to find the layout of dependencies between AU nodes of micro-expression classification.Finally, multiple attentional features of each facial action are enriched with Transformer model to include more sequence information before calculating the overall correlation of each region.The proposed method is validated in CASME II and CAS(ME)^2 datasets, and the recognition rate reached 69.85%.
文摘Facial micro-expressions are short and imperceptible expressions that involuntarily reveal the true emotions that a person may be attempting to suppress,hide,disguise,or conceal.Such expressions can reflect a person's real emotions and have a wide range of application in public safety and clinical diagnosis.The analysis of facial micro-expressions in video sequences through computer vision is still relatively recent.In this research,a comprehensive review on the topic of spotting and recognition used in micro expression analysis databases and methods,is conducted,and advanced technologies in this area are summarized.In addition,we discuss challenges that remain unresolved alongside future work to be completed in the field of micro-expression analysis.
基金This work is funded by the natural science foundation of Jiangsu Province(No.BK20150471)the natural science foundation of the higher education institutions of Jiangsu Province(No.17KJB520007)+2 种基金the Key Research and Development Program of Zhenjiang-Social Development(No.SH2018005)the scientific researching fund of Jiangsu University of Science and Technology(No.1132921402,No.1132931803)the basic science and frontier technology research program of Chongqing Municipal Science and Technology Commission(cstc2016jcyjA0407).
文摘Micro-expression recognition has attracted growing research interests in the field of compute vision.However,micro-expression usually lasts a few seconds,thus it is difficult to detect.This paper presents a new framework to recognize micro-expression using pyramid histogram of Centralized Gabor Binary Pattern from Three Orthogonal Panels(CGBP-TOP)which is an extension of Local Gabor Binary Pattern from Three Orthogonal Panels feature.CGBP-TOP performs spatial and temporal analysis to capture the local facial characteristics of micro-expression image sequences.In order to keep more local information of the face,CGBP-TOP is extracted based on pyramid subregions of the micro-expression video frame.The combination of CGBP-TOP and spatial pyramid can represent well and truly the facial movements of the micro-expression image sequences.However,the dimension of our pyramid CGBP-TOP tends to be very high,which may lead to high data redundancy problem.In addition,it is clear that people of different genders usually have different ways of micro-expression.Therefore,in this paper,in order to select the relevant features of micro-expression,the gender-specific sparse multi-task learning method with adaptive regularization term is adopted to learn a compact subset of pyramid CGBP-TOP feature for micro-expression classification of different sexes.Finally,extensive experiments on widely used CASME II and SMIC databases demonstrate that our method can efficiently extract micro-expression motion features in the micro-expression video clip.Moreover,our proposed approach achieves comparable results with the state-of-the-art methods.
基金supported by the National Natural Science Foundation of Hunan Province,China(Grant Nos.2021JJ50058,2022JJ50051)the Open Platform Innovation Foundation of Hunan Provincial Education Department(Grant No.20K046)The Scientific Research Fund of Hunan Provincial Education Department,China(Grant Nos.21A0350,21C0439,19A133).
文摘Aiming at the problems of short duration,low intensity,and difficult detection of micro-expressions(MEs),the global and local features of ME video frames are extracted by combining spatial feature extraction and temporal feature extraction.Based on traditional convolution neural network(CNN)and long short-term memory(LSTM),a recognition method combining global identification attention network(GIA),block identification attention network(BIA)and bi-directional long short-term memory(Bi-LSTM)is proposed.In the BIA,the ME video frame will be cropped,and the training will be carried out by cropping into 24 identification blocks(IBs),10 IBs and uncropped IBs.To alleviate the overfitting problem in training,we first extract the basic features of the preprocessed sequence through the transfer learning layer,and then extract the global and local spatial features of the output data through the GIA layer and the BIA layer,respectively.In the BIA layer,the input data will be cropped into local feature vectors with attention weights to extract the local features of the ME frames;in the GIA layer,the global features of the ME frames will be extracted.Finally,after fusing the global and local feature vectors,the ME time-series information is extracted by Bi-LSTM.The experimental results show that using IBs can significantly improve the model’s ability to extract subtle facial features,and the model works best when 10 IBs are used.
基金Shaanxi Province Key Research and Development Project(No.2021 GY-280)Shaanxi Province Natural Science Basic Research Program Project(No.2021JM-459)+1 种基金National Natural Science Foundation of China(No.61834005,61772417,61802304,61602377,61634004)Shaanxi Province International Science and Technology Cooperation Project(No.2018KW-006)。
文摘Aiming at the problem of unsatisfactory effects of traditional micro-expression recognition algorithms,an efficient micro-expression recognition algorithm is proposed,which uses convolutional neural networks(CNN)to extract spatial features of micro-expressions,and long short-term memory network(LSTM)to extract time domain features.CNN and LSTM are combined as the basis of micro-expression recognition.In many CNN structures,the visual geometry group(VGG)using a small convolution kernel is finally selected as the pre-network through comparison.Due to the difficulty of deep learning training and over-fitting,the dropout method and batch normalization method are used to solve the problem in the VGG network.Two data sets CASME and CASME II are used for test comparison,in order to solve the problem of insufficient data sets,randomly determine the starting frame,and a fixedlength frame sequence is used as the standard,and repeatedly read all sample frames of the entire data set to achieve trayersal and data amplification.Finallv.a hieh recognition rate of 67.48% is achieved.
基金the National Natural Science Foundation of China(Nos.61772417,61634004,and 61602377)the Key R&D Progrm Projects in Shaanxi Province(No.2017GY-060)the Shaanxi Natural Science Basic Research Project(No.018JM4018)。
文摘The intensity of the micro-expression is weak,although the directional low frequency components in the image are preserved by many algorithms,the extracted micro-expression ft^ature information is not sufficient to accurately represent its sequences.In order to improve the accuracy of micro-expression recognition,first,each frame image is extracted from,its sequences,and the image frame is pre-processed by using gray normalization,size normalization,and two-dimensional principal component analysis(2DPCA);then,the optical flow method is used to extract the motion characteristics of the reduced-dimensional image,the information entropy value of the optical flow characteristic image is calculated by the information entropy principle,and the information entropy value is analyzed to obtain the eigenvalue.Therefore,more micro-expression feature information is extracted,including more important information,which can further improve the accuracy of micro-expression classification and recognition;finally,the feature images are classified by using the support vector machine(SVM).The experimental results show that the micro-expression feature image obtained by the information entropy statistics can effectively improve the accuracy of micro-expression recognition.
基金Supported by the Shaanxi Province Key Research and Development Project(No.2021GY-280)Shaanxi Province Natural Science Basic Re-search Program Project(No.2021JM-459)+1 种基金the National Natural Science Foundation of China(No.61834005,61772417,61802304,61602377,61634004)the Shaanxi Province International Science and Technology Cooperation Project(No.2018KW-006).
文摘The micro-expression lasts for a very short time and the intensity is very subtle.Aiming at the problem of its low recognition rate,this paper proposes a new micro-expression recognition algorithm based on a three-dimensional convolutional neural network(3D-CNN),which can extract two-di-mensional features in spatial domain and one-dimensional features in time domain,simultaneously.The network structure design is based on the deep learning framework Keras,and the discarding method and batch normalization(BN)algorithm are effectively combined with three-dimensional vis-ual geometry group block(3D-VGG-Block)to reduce the risk of overfitting while improving training speed.Aiming at the problem of the lack of samples in the data set,two methods of image flipping and small amplitude flipping are used for data amplification.Finally,the recognition rate on the data set is as high as 69.11%.Compared with the current international average micro-expression recog-nition rate of about 67%,the proposed algorithm has obvious advantages in recognition rate.
文摘Background The use of micro-expression recognition to recognize human emotions is one of the most critical challenges in human-computer interaction applications. In recent years, cross-database micro-expression recognition(CDMER) has emerged as a significant challenge in micro-expression recognition and analysis. Because the training and testing data in CDMER come from different micro-expression databases, CDMER is more challenging than conventional micro-expression recognition. Methods In this paper, an adaptive spatio-temporal attention neural network(ASTANN) using an attention mechanism is presented to address this challenge. To this end, the micro-expression databases SMIC and CASME II are first preprocessed using an optical flow approach,which extracts motion information among video frames that represent discriminative features of micro-expression.After preprocessing, a novel adaptive framework with a spatiotemporal attention module was designed to assign spatial and temporal weights to enhance the most discriminative features. The deep neural network then extracts the cross-domain feature, in which the second-order statistics of the sample features in the source domain are aligned with those in the target domain by minimizing the correlation alignment(CORAL) loss such that the source and target databases share similar distributions. Results To evaluate the performance of ASTANN, experiments were conducted based on the SMIC and CASME II databases under the standard experimental evaluation protocol of CDMER. The experimental results demonstrate that ASTANN outperformed other methods in relevant crossdatabase tasks. Conclusions Extensive experiments were conducted on benchmark tasks, and the results show that ASTANN has superior performance compared with other approaches. This demonstrates the superiority of our method in solving the CDMER problem.
文摘Biometric recognition refers to the process of recognizing a person’s identity using physiological or behavioral modalities,such as face,voice,fingerprint,gait,etc.Such biometric modalities are mostly used in recognition tasks separately as in unimodal systems,or jointly with two or more as in multimodal systems.However,multimodal systems can usually enhance the recognition performance over unimodal systems by integrating the biometric data of multiple modalities at different fusion levels.Despite this enhancement,in real-life applications some factors degrade multimodal systems’performance,such as occlusion,face poses,and noise in voice data.In this paper,we propose two algorithms that effectively apply dynamic fusion at feature level based on the data quality of multimodal biometrics.The proposed algorithms attempt to minimize the negative influence of confusing and low-quality features by either exclusion or weight reduction to achieve better recognition performance.The proposed dynamic fusion was achieved using face and voice biometrics,where face features were extracted using principal component analysis(PCA),and Gabor filters separately,whilst voice features were extracted using Mel-Frequency Cepstral Coefficients(MFCCs).Here,the facial data quality assessment of face images is mainly based on the existence of occlusion,whereas the assessment of voice data quality is substantially based on the calculation of signal to noise ratio(SNR)as per the existence of noise.To evaluate the performance of the proposed algorithms,several experiments were conducted using two combinations of three different databases,AR database,and the extended Yale Face Database B for face images,in addition to VOiCES database for voice data.The obtained results show that both proposed dynamic fusion algorithms attain improved performance and offer more advantages in identification and verification over not only the standard unimodal algorithms but also the multimodal algorithms using standard fusion methods.
基金supported by the Science and Technology Development Fund of Macao(No.0035/2023/ITP1)the National Natural Science Foundation of China(Nos.U1836220 and 61672267)+2 种基金the Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.KYCX19_1616)the Qing Lan Talent Program of Jiangsu ProvinceJiangsu Province Key Research and Development Plan(Industry Foresight and Key Core Technology)-Competitive Project(No.BE2020036).
文摘Micro-Expression Recognition(MER)is a challenging task as the subtle changes occur over different action regions of a face.Changes in facial action regions are formed as Action Units(AUs),and AUs in micro-expressions can be seen as the actors in cooperative group activities.In this paper,we propose a novel deep neural network model for objective class-based MER,which simultaneously detects AUs and aggregates AU-level features into micro-expression-level representation through Graph Convolutional Networks(GCN).Specifically,we propose two new strategies in our AU detection module for more effective AU feature learning:the attention mechanism and the balanced detection loss function.With these two strategies,features are learned for all the AUs in a unified model,eliminating the error-prune landmark detection process and tedious separate training for each AU.Moreover,our model incorporates a tailored objective class-based AU knowledge-graph,which facilitates the GCN to aggregate the AU-level features into a micro-expression-level feature representation.Extensive experiments on two tasks in MEGC 2018 show that our approach outperforms the current state-of-the-art methods in MER.Additionally,we also report our single model-based micro-expression AU detection results.
基金supported by the Science and Technology Development Fund of Macao,China(No.0035/2023/ITP1)the National Natural Science Foundation of China(No.62076122)+2 种基金the Basic Science(Natural Science)Research Project of Higher Education Institutions in Jiangsu Province(No.24KJA520003)the 333 High-Level Talents in Jiangsu Province(2024)the Fundamental Research Funds for the Central Universities(No.2242024k30027).
文摘As mobile devices and sensor technology advance,their role in communication becomes increasingly indispensable.Micro-expression recognition,an invaluable non-verbal communication method,has been extensively studied in human-computer interaction,sentiment analysis,and security fields.However,the sensitivity and privacy implications of micro-expression data pose significant challenges for centralized machine learning methods,raising concerns about serious privacy leakage and data sharing.To address these limitations,we investigate a federated learning scheme tailored specifically for this task.Our approach prioritizes user privacy by employing federated optimization techniques,enabling the aggregation of clients’knowledge in an encrypted space without compromising data privacy.By integrating established micro-expression recognition methods into our framework,we demonstrate that our approach not only ensures robust data protection but also maintains high recognition performance comparable to non-privacy-preserving mechanisms.To our knowledge,this marks the first application of federated learning to the micro-expression recognition task.
基金supported by the NSFC–Zhejiang Joint Fund of the Integration of Informatization and Industrialization under Grant No.U1909210the the National Natural Science Foundation of China under Grant No.61772312the Fundamental Research Funds of Shandong University(Grant No.2018JC030)。
文摘Micro-expression recognition is a substantive cross-study of psychology and computer science,and it has a wide range of applications(e.g.,psychological and clinical diagnosis,emotional analysis,criminal investigation,etc.).However,the subtle and diverse changes in facial muscles make it difficult for existing methods to extract effective features,which limits the improvement of micro-expression recognition accuracy.Therefore,we propose a multi-scale joint feature network based on optical flow images for micro-expression recognition.First,we generate an optical flow image that reflects subtle facial motion information.The optical flow image is then fed into the multi-scale joint network for feature extraction and classification.The proposed joint feature module(JFM)integrates features from different layers,which is beneficial for the capture of micro-expression features with different amplitudes.To improve the recognition ability of the model,we also adopt a strategy for fusing the feature prediction results of the three JFMs with the backbone network.Our experimental results show that our method is superior to state-of-the-art methods on three benchmark datasets(SMIC,CASME II,and SAMM)and a combined dataset(3 DB).
基金supported by the National Natural Science Foundation of China(No.62102180)the Research Grants Council of Hong Kong(Collaborative Research Fund No.C7055-21GF)the Hong Kong Scholars Program,and the Natural Science Foundation of Jiangsu Province(No.BK20210329).
文摘Micro-expressions are spontaneous,rapid and subtle facial movements that can hardly be suppressed or fabricated.Micro-expression recognition(MER)is one of the most challenging topics in affective computing.It aims to recognize subtle facial movements which are quite difficult for humans to perceive in a fleeting period.Recently,many deep learning-based MER methods have been developed.However,how to effectively capture subtle temporal variations for robust MER still perplexes us.We propose a counterfactual discriminative micro-expression recognition(CoDER)method to effectively learn the slight temporal variations for video-based MER.To explicitly capture the causality from temporal dynamics hidden in the micro-expression(ME)sequence,we propose ME counterfactual reasoning by comparing the effects of the facts w.r.t.original ME sequences and the counterfactuals w.r.t.counterfactually-revised ME sequences,and then perform causality-aware prediction to encourage the model to learn those latent ME temporal cues.Extensive experiments on four widely-used ME databases demonstrate the effectiveness of CoDER,which results in comparable and superior MER performance compared with that of the state-of-the-art methods.The visualization results show that CoDER successfully perceives the meaningful temporal variations in sequential faces.
