Micro-expression spotting is a fundamental step in the micro-expression analysis. This paper proposes a novel network based convolutional neural network (CNN) for spotting multi-scale spontaneous ...micro-expression intervals in long videos. We named the network as Micro-Expression Spotting Network (MESNet). It is composed of three modules. The first module is a 2+1D Spatiotemporal Convolutional Network, which uses 2D convolution to extract spatial features and 1D convolution to extract temporal features. The second module is a Clip Proposal Network, which gives some proposed micro-expression clips. The last module is a Classification Regression Network, which classifies the proposed clips to micro-expression or not, and further regresses their temporal boundaries. We also propose a novel evaluation metric for spotting micro-expression. Extensive experiments have been conducted on the two long video datasets: CAS(ME) 2 and SAMM, and the leave-one-subject-out cross-validation is used to evaluate the spotting performance. Results show that the proposed MESNet effectively enhances the F1-score metric. And comparative results show the proposed MESNet has achieved a good performance, which outperforms other state-of-the-art methods, especially in the SAMM dataset.
A novel SARS-related coronavirus (SARS-CoV-2) has recently emerged as a serious pathogen that causes high morbidity and substantial mortality. However, the mechanisms by which SARS-CoV-2 evades host ...immunity remain poorly understood. Here, we identified SARS-CoV-2 membrane glycoprotein M as a negative regulator of the innate immune response. We found that the M protein interacted with the central adaptor protein MAVS in the innate immune response pathways. This interaction impaired MAVS aggregation and its recruitment of downstream TRAF3, TBK1, and IRF3, leading to attenuation of the innate antiviral response. Our findings reveal a mechanism by which SARS-CoV-2 evades the innate immune response and suggest that the M protein of SARS-CoV-2 is a potential target for the development of SARS-CoV-2 interventions.
ASFV is a large DNA virus that is highly pathogenic in domestic pigs. How this virus is sensed by the innate immune system as well as why it is so virulent remains enigmatic. In this study, we show ...that the ASFV genome contains AT-rich regions that are recognized by the DNA-directed RNA polymerase III (Pol-III), leading to viral RNA sensor RIG-I-mediated innate immune responses. We further show that ASFV protein I267L inhibits RNA Pol-III-RIG-I-mediated innate antiviral responses. I267L interacts with the E3 ubiquitin ligase Riplet, disrupts Riplet-RIG-I interaction and impairs Riplet-mediated K63-polyubiquitination and activation of RIG-I. I267L-deficient ASFV induces higher levels of interferon-β, and displays compromised replication both in primary macrophages and pigs compared with wild-type ASFV. Furthermore, I267L-deficiency attenuates the virulence and pathogenesis of ASFV in pigs. These findings suggest that ASFV I267L is an important virulence factor by impairing innate immune responses mediated by the RNA Pol-III-RIG-I axis.
A robust automatic micro-expression recognition system would have broad applications in national safety, police interrogation, and clinical diagnosis. Developing such a system requires high quality ...databases with sufficient training samples which are currently not available. We reviewed the previously developed micro-expression databases and built an improved one (CASME II), with higher temporal resolution (200 fps) and spatial resolution (about 280×340 pixels on facial area). We elicited participants' facial expressions in a well-controlled laboratory environment and proper illumination (such as removing light flickering). Among nearly 3000 facial movements, 247 micro-expressions were selected for the database with action units (AUs) and emotions labeled. For baseline evaluation, LBP-TOP and SVM were employed respectively for feature extraction and classifier with the leave-one-subject-out cross-validation method. The best performance is 63.41% for 5-class classification.
Organic materials have gained considerable attention for electrochromic (EC) applications owing to improved EC performance and good processability. As a class of well-recognized organic EC materials, ...viologens have received persistent attention due to the structural versatility and property tunability, and are major active EC components for most of the marketed EC devices. Over the past two decades, extensive efforts have been made to design and synthesize different types of viologen-based materials with enhanced EC properties. This review summarizes chemical structures, preparation and EC properties of various latest viologen-based electrochromes, including small viologen derivatives, main-chain viologen-based polymers, conjugated polymers with viologen side-chains and viologen-based organic/inorganic composites. The performance enhancement mechanisms are concisely discussed. The current marketed viologens-based electrochromic devices (ECDs) are briefly introduced and an outlook on the challenges and future exploration directions for viologen-based materials and their ECDs are also proposed.
•All the publications related to the roles of melatonin in fruit have been reviewed for the first time.•The signalling pathways activated by melatonin have been traced.•The contradictory reports and ...the issues that must be clarified in further works have been discussed.
Melatonin (MLT) is a versatile biological signal that is involved in a number of plant processes, including germination, development, flowering, photosynthesis and defence. The need to develop new methodologies for enhancing crop yields and extending fruit postharvest preservation, together with the beneficial effects of dietary MLT, have stimulated the study of the availability and biological roles of MLT in fruit. Here, we are reviewing for the first time the effects of endogenous and exogenous MLT on fruit production and postharvest preservation. The signalling pathways implicated in MLT response and the applications of MLT in fruit decay, abiotic stress and pathogen infection have been traced in order to provide new insights on the biological significance of MLT in fruit.
Alcohol use disorder (AUD) is an important brain disease. It alters the brain structure. Recently, scholars tend to use computer vision based techniques to detect AUD. We collected 235 subjects, 114 ...alcoholic and 121 non-alcoholic. Among the 235 image, 100 images were used as training set, and data augmentation method was used. The rest 135 images were used as test set. Further, we chose the latest powerful technique—convolutional neural network (CNN) based on convolutional layer, rectified linear unit layer, pooling layer, fully connected layer, and softmax layer. We also compared three different pooling techniques: max pooling, average pooling, and stochastic pooling. The results showed that our method achieved a sensitivity of 96.88%, a specificity of 97.18%, and an accuracy of 97.04%. Our method was better than three state-of-the-art approaches. Besides, stochastic pooling performed better than other max pooling and average pooling. We validated CNN with five convolution layers and two fully connected layers performed the best. The GPU yielded a 149× acceleration in training and a 166× acceleration in test, compared to CPU.
•Developing the combination rule for evidences by introducing trust as the third parameter, following weight and reliability.•Proposing a more generalized method for full stage group decision-making ...with a broader range of application.•Presenting a fresh perspective on achieving consensus based on the relationships among trust, weight, and reliability.•Proposing a novel method for dynamically determining weight and reliability parameters based on their respective definitions.
Recent studies on group decision-making (GDM) have highlighted the significance of the reliability parameter, which is considered to be the second critical parameter, after weight, of an information source. In practice, trust among decision makers (DMs) also should receive attention because of the interaction among DMs. Thus, in this study, we introduce trust as a third parameter and focus on differentiating among these three information parameters. First, we apply the generalized combination (GC) rule to extract and fuse individual information. Then, we implement the procedures of consensus measure and information selection based on similarity. Next, we adjust the selected inconsistent information using trust-based weight and reliability parameters to facilitate group consensus. During the consensus reaching process, the weight and reliability parameters are dynamically and differentially determined. Finally, the proposed method is summarized as a GDM framework. We introduce a case simulation study to verify the feasibility of the proposed method and conduct a numerical comparison and comparative discussion to demonstrate that the proposed method provides a fresh perspective on developing GDM with consensus. In particular, this framework is suitable for addressing GDM problems involving uncertainty in high-dimensional information with wide discrepancy.
This study focuses on advancing the field of remote sensing image target detection, addressing challenges such as small target detection, complex background handling, and dense target distribution. ...We propose solutions based on enhancing the YOLOv7 algorithm. Firstly, we improve the multi-scale feature enhancement (MFE) method of YOLOv7, enhancing its adaptability and precision in detecting small targets and complex backgrounds. Secondly, we design a modified YOLOv7 global information DP-MLP module to effectively capture and integrate global information, thereby improving target detection accuracy and robustness, especially in handling large-scale variations and complex scenes. Lastly, we explore a semi-supervised learning model (SSLM) target detection algorithm incorporating unlabeled data, leveraging information from unlabeled data to enhance the model's generalization ability and performance. Experimental results demonstrate that despite the outstanding performance of YOLOv7, the mean average precision (MAP) can still be improved by 1.9%. Specifically, under testing on the TGRS-HRRSD-Dataset, the MFE and DP-MLP models achieve MAP values of 93.4% and 93.1%, respectively. Across the NWPU VHR-10 dataset, the three models achieve MAP values of 93.1%, 92.1%, and 92.2%, respectively. Significant improvements are observed across various metrics compared to the original model. This study enhances the adaptability, accuracy, and generalization of remote sensing image object detection.
Unlike the conventional facial expressions, micro-expressions are involuntary and transient facial expressions capable of revealing the genuine emotions that people attempt to hide. Therefore, they ...can provide important information in a broad range of applications such as lie detection, criminal detection, etc. Since micro-expressions are transient and of low intensity, however, their detection and recognition is difficult and relies heavily on expert experiences. Due to its intrinsic particularity and complexity, video-based micro-expression analysis is attractive but challenging, and has recently become an active area of research. Although there have been numerous developments in this area, thus far there has been no comprehensive survey that provides researchers with a systematic overview of these developments with a unified evaluation. Accordingly, in this survey paper, we first highlight the key differences between macro- and micro-expressions, then use these differences to guide our research survey of video-based micro-expression analysis in a cascaded structure, encompassing the neuropsychological basis, datasets, features, spotting algorithms, recognition algorithms, applications and evaluation of state-of-the-art approaches. For each aspect, the basic techniques, advanced developments and major challenges are addressed and discussed. Furthermore, after considering the limitations of existing micro-expression datasets, we present and release a new dataset - called micro-and-macro expression warehouse (MMEW) - containing more video samples and more labeled emotion types. We then perform a unified comparison of representative methods on CAS(ME)<inline-formula><tex-math notation="LaTeX">^2</tex-math> <mml:math><mml:msup><mml:mrow/><mml:mn>2</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="liu-ieq1-3067464.gif"/> </inline-formula> for spotting, and on MMEW and SAMM for recognition, respectively. Finally, some potential future research directions are explored and outlined.