General Recognition Research Articles

Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOI

Detecting human-object interactions (HOI) in a few-shot setting remains a challenge. Existing meta-learning methods struggle to extract representative features for classification due to the limited data, while existing few-shot HOI models rely on HOI text labels for classification. Moreover, some query images may display visual similarity to those outside their class, such as similar backgrounds between different HOI classes. This makes learning more challenging, especially with limited samples. Bongard-HOI epitomizes this HOI few-shot problem, making it the benchmark we focus on in this paper. In our proposed method, we introduce novel label-uncertain query augmentation techniques to enhance the diversity of the query inputs, aiming to distinguish the positive HOI class from the negative ones. As these augmented inputs may or may not have the same class label as the original inputs, their class label is unknown. Those belonging to a different class become hard samples due to their visual similarity to the original ones. Additionally, we introduce a novel pseudo-label generation technique that enables a mean teacher model to learn from the augmented label-uncertain inputs. We propose to augment the negative support set for the student model to enrich the semantic information, fostering diversity that challenges and enhances the student’s learning. Experimental results demonstrate that our method sets a new state-of-the-art (SOTA) performance by achieving 68.74% accuracy on the Bongard-HOI benchmark, a significant improvement over the existing SOTA of 66.59%. In our evaluation on HICO-FS, a more general few-shot recognition dataset, our method achieves 73.27% accuracy, outperforming the previous SOTA of 71.20% in the 5- way 5-shot task.

Differential contributions of the hippocampal dentate gyrus and CA1 subfield to mnemonic discrimination.

Evidence suggests that individual hippocampal subfields are preferentially involved in various memory-related processes. Here, we demonstrated dissociations in these memory processes in two unique individuals with near-selective bilateral damage within the hippocampus, affecting the dentate gyrus (DG) in case BL and the cornu ammonis 1 (CA1) subfield in case BR. BL was impaired in discriminating highly similar objects in memory (i.e., mnemonic discrimination) but exhibited preserved overall recognition of studied objects, regardless of similarity. Conversely, BR demonstrated impaired general recognition. These results provide evidence for the DG in discrimination processes, likely related to underlying pattern separation computations, and the CA1 in retention/retrieval.

Multiple-source distribution deep adaptive feature norm network for EEG emotion recognition.

Electroencephalogram (EEG) emotion recognition plays an important role in human-computer interaction, and a higher recognition accuracy can improve the user experience. In recent years, domain adaptive methods in transfer learning have been used to construct a general emotion recognition model to deal with domain difference among different subjects and sessions. However, it is still challenging to effectively reduce domain difference in domain adaptation. In this paper, we propose a Multiple-Source Distribution Deep Adaptive Feature Norm Network for EEG emotion recognition, which reduce domain difference by improving the transferability of task-specific features. In detail, the domain adaptive method of our model employs a three-layer network topology, inserts Adaptive Feature Norm to self-supervised adjustment between different layers, and combines a multiple-kernel selection approach to mean embedding matching. The method proposed in this paper achieves the best classification performance in the SEED and SEED-IV datasets. In SEED dataset, the average accuracy of cross-subject and cross-session experiments is 85.01 and 91.93%, respectively. In SEED-IV dataset, the average accuracy is 58.81% in cross-subject experiments and 59.51% in cross-session experiments. The experimental results demonstrate that our method can effectively reduce the domain difference and improve the emotion recognition accuracy.

Face-Inception-Net for Recognition

Face recognition in general scenarios has been saturated in recent years, but there is still room to enhance model performance in extreme scenarios and fairness situations. Inspired by the successful application of Transformer and ConvNet in computer vision, we propose a FIN-Block, which gives a more flexible composition paradigm for building a novel pure convolution model and provides a foundation for constructing a new framework for general face recognition in both extreme scenarios and fairness situations. FIN-Block-A uses a combination of stacked large-size convolution kernels and parallel convolution branches to ensure a large spatial receptive field while improving the module’s deep feature embedding and extraction capabilities. FIN-Block-B takes advantage of stacked orthogonal convolution kernels and parallel branches to balance model size and performance. By applying FIN-Block with an adapted convolution kernel size in different stages, we built a reasonable and novel framework Face-Inception-Net, and the performance of the model is highly competitive with ConvNeXt and InceptionNeXt. The models were trained on CASIA-WebFace and MS-wo-RFW databases and evaluated on 14 mainstream benchmarks, including LFW, extreme scene, and fairness test sets. The proposed Face-Inception-Net achieved the highest average TAR@FAR0.001 of 95.9% in all used benchmarks, fully demonstrating effectiveness and generality in various scenarios.

Face shape and motion are perceptually separable: Support for a revised model of face processing.

A recent model of face processing proposes that face shape and motion are processed in parallel brain pathways. Although tested in neuroimaging, the assumptions of this theory remain relatively untested through controlled psychophysical studies until now. Recruiting undergraduate students over the age of 18, we test this hypothesis using a tight control of stimulus factors, through computerized three-dimensional face models and calibration of dimensional discriminability, and of decisional factors, through a model-based analysis using general recognition theory (GRT). Theoretical links between neural and perceptual forms of independence within GRT allowed us to derive the a priori hypotheses that perceptual separability of shape and motion should hold, while other forms of independence defined within GRT might fail. We found evidence to support both of those predictions.

Distinct cytoskeletal regulators of mechanical memory in cardiac fibroblasts and cardiomyocytes.

Recognizing that cells "feel" and respond to their mechanical environment, recent studies demonstrate that many cells exhibit a phenomenon of "mechanical memory" in which features induced by prior mechanical cues persist after the mechanical stimulus has ceased. While there is a general recognition that different cell types exhibit different responses to changes in extracellular matrix stiffening, the phenomenon of mechanical memory within myocardial cell types has received little attention to date. To probe the dynamics of mechanical memory in cardiac fibroblasts (CFs) and cardiomyocytes derived from human induced pluripotent stem cells (iPSC-CMs), we employed a magnetorheological elastomer (MRE) cell culture substrate with tunable and reversible stiffness spanning the range from normal to diseased myocardium. In CFs, using increased cell area and increases in α-smooth muscle actin as markers of cellular responses to matrix stiffening, we found that induction of mechanical memory required seven days of stiff priming. Both induction and maintenance of persistent CF activation were blocked with the F-actin inhibitor cytochalasin D, while inhibitors of microtubule detyrosination had no impact on CFs. In iPSC-CMs, mechanical memory was invoked after only 24h of stiff priming. Moreover, mechanical memory induction and maintenance were microtubule-dependent in CMs with no dependence on F-actin. Overall, these results identify the distinct temporal dynamics of mechanical memory in CFs and iPSC-CMs with different cytoskeletal mediators responsible for inducing and maintaining the stiffness-activated phenotype. Due to its flexibility, this model is broadly applicable to future studies interrogating mechanotransduction and mechanical memory in the heart and might inform strategies for attenuating the impact of load-induced pathology and excess myocardial stiffness.

IGG in the trenches: Results of an in-depth interview study on the practice, politics, and future of investigative genetic genealogy

Investigative genetic genealogy (IGG) is a new technique for identifying criminal suspects and unidentified deceased and living persons that has sparked controversy. In a criminal case, the technique involves uploading genetic information left by a putative perpetrator at the crime scene to one or more direct-to-consumer genetic genealogy databases with the intention of identifying the perpetrator's genetic relatives and, eventually, locating the perpetrator on the family tree. In 2018, IGG helped to identify the Golden State Killer, and it has since been used in hundreds of investigations in the United States. Here, we report findings from in-depth interviews with 24 U.S.-based individuals involved in IGG that are relevant to the technique’s current practice and predicted future. Key findings include: an emphasis on restricting IGG as a conceptual and technical matter to lead generation; the rapid growth of a private and largely self-regulating industry to support IGG; general recognition of three categories of cases associated with distinct practical, ethical, and policy questions, as well as varying degrees of controversy; and the significant influence of perceived public opinion on IGG practice. The experiences and perspectives of individuals in the IGG trenches related to these and other issues are potentially useful inputs to ongoing efforts to regulate the technique.

The Role of Mobile Applications in a Foreign Language Learning

In the era of digitization, the traditional teaching method is not a sufficiently effective tool in increasing the level of information acquisition. One method to improve the educational program can be the introduction of a variety of content, technological or not, which occupies a noteworthy place in enhancing learning effectiveness. The purpose of the study was to determine the impact of using mobile applications on the success of students in learning a foreign language. To achieve the goal, the comparative method, testing, surveys, and statistical methods of analysis were used. The results showed a statistically significant difference in the vocabulary of the students of the experimental group when comparing the results before and after the study. EG student engagement, attention focus, and immersion in educational programs using mobile applications received relatively high marks. The study provides preliminary empirically supported results that indicate that mobile applications can be attractive and highly effective in foreign language learning. The practical value of the study is that the results demonstrate that teachers can benefit from the fact that students will use mobile applications to enhance their vocabulary performance when learning a new language. By general recognition, mobile applications are exceptionally convenient to use, and students demonstrate better results in learning as compared to students who took a course according to a traditional program. A promising research perspective can be the use of artificial intelligence for learning a foreign language in institutions of higher education.

Recognizing Complex Activities by Combining Sequences of Basic Motions

For daily motion recognition, each researcher builds their own method to recognize their own specific target actions. However, for other types of target motions, they cannot use their method to recognize other kinds of motions because the features of their target motions that they extracted cannot be extracted from other kinds of motions. Therefore, we wanted to develop a general method that can be used in most kinds of motions. From our observations, we found that a meaningful motion is combined with some basic motions. Therefore, we could recognize basic motions and then combine them to recognize a target motion. First, we simply defined the basic motions according to the sensor’s basic sensing directions. Second, we used k-nearest neighbors (KNN) and dynamic time warping (DTW) to recognize different categories of basic motions. Then, we gave each basic motion a specific number to represent it, and finally, used continuous dynamic programming (CDP) to recognize a target motion by the sequence of basic motions we collected. In our experiment on our basic motions, the accuracy of all of the basic motions is higher than 80%, so the recognition of basic motions is reliable. Then, we performed an experiment for recognizing the target motions. The results of recognizing the target motions were not good, the average accuracy being only 65.9%, and we still have to improve our system. However, we also compared our system with recognizing motions by using another general recognition method, KNN. And the average accuracy of using KNN to recognize motions was 53.4%. As this result shows, our method still obtains better results in recognizing different kinds of motions than using KNN.

Pricing Models under Three-Echelon Prefabricated Construction Supply Chains with Consumer Preferences

With the growing ecological crisis and consumer environmental awareness, there is a general recognition of the urgent need for the reform of the energy-intensive construction industry. Prefabricated construction has emerged as an effective approach to achieve energy conservation and environmental sustainability. The prefabricated rate is a critical indicator that comprehensively reflects the level of technology, which affects orders, costs, pricing, and partnerships. Moreover, given the highly decentralized nature of the construction industry, it is imperative to consider building materials’ supply in the Prefabricated Construction Supply Chain (PCSC). Therefore, this paper investigates how the prefabricated rate affects consumer preferences and order allocation while designing a three-echelon PCSC under a single-supplier structure, two-supplier structure, and dual-channel structure. Two different channels, prefabricated component and non-prefabricated component, are distinguished by the prefabricated rate. This research not only provides pricing-oriented decision advice but also offers suggestions for channel selection among participants. The results show that the increase in consumers’ preference for the prefabricated rate raises prices. Moreover, a moderate prefabricated rate is most beneficial. Comparing the three models, the supply chain performance of a two-supplier structure is better than that of a single-supplier structure if the prefabricated rate exceeds a certain threshold, while the dual-channel structure is the worst.

A multispectral vision-based machine learning framework for non-contact vehicle weigh-in-motion

The present study proposes an automated non-contact weigh-in-motion framework using multispectral vision and machine learning method, which provides an all-weather monitoring of heavy vehicles on transportation infrastructures. Multispectral based computer vision techniques consist of two steps, one is acquiring the tire deformation parameters from thermal imaging camera and the latter is obtaining the sidewall characters from the ordinary one. A novel edge detection algorithm is designed for thermal image-based tire deformation estimation. A general recognition model with well-established tire characters database for universal tire sidewall markings, such as non-standard fonts or non-text characters, curved markings or inverted markings, and is developed based on Efficient neural network (E-NET) and YOLOV5S methods. A machine learning-based model for estimating the various vehicles tire-roadway contact forces is established based on eXtreme Gradient Boosting (XGBoost). A database of different vehicles’ tires with a total of 1127 samples from 19 types of tires and 648 of laboratory datasets from common vehicles are collected to train the model. The Bayesian optimization is employed to capture the optimal model, and a hybrid training strategy including biased data is applied to update the model. An importance analysis for 11 features is conducted to validate the performance proposed model. The accuracy, feasibility, and effectiveness of the proposed method is carefully investigated by field experiments for trucks and sport utility vehicles under static and low-speed drive. A maximum of 5 % difference is witnessed by comparing the results with that of the traditional WIM system. The present method presents a cost-effective means with no sensors on structures for vehicle weighting, that demonstrates a great potential to implement in toll station, highway infrastructures as well as health monitoring of civil engineering fields.

Liturgical features of the Neocatechumenal Way movement in the context of integration into the structure of the Roman Catholic Church

The Neocatechumenal Way (Neocatechumenate) is a movement that emerged within the Roman Catholic Church during the Second Vatican Council. Its main mission is to bring into the Church baptised persons who, for various reasons, are distant from the life of the Church. Because of its liturgical peculiarities, the Catholic movement has received mixed reviews from scholars. On the one hand, Western theologians have been positive about the activities of the Neocatechumenal Way, especially in terms of the results of ecclesialisation. On the other hand, some researchers and representatives of the church hierarchy and clergy reacted negatively to the closed nature of the church communities, the sacramentology and the practices of churching. The article attempts to identify and analyse the liturgical characteristics of the Neocatechumenal Way and their role in the process of integrating the movement into the structure of the Roman Catholic Church. In order to achieve this, the author has examined a number of sources that provide insights into the specifics of the Neocatechumenal worship. The central question addressed in the article is why the Catholic hierarchy refused to accept the liturgical particularities of the movement, despite its general recognition as a legitimate way of being church. The author suggests that the leaders of the movement based their liturgical practices on the theological concept of “communion” — a central ecclesiological idea of the Second Vatican Council — and sought to renew parish life. In the process of reform, however, the movement rejected a significant part of the Roman Catholic Church’s liturgical heritage and challenged the institutional form of the Eucharistic community.

Characterization of Lactobacillus spp. as Probiotic and Antidiabetic Potential Isolated from Boza, Traditional Fermented Beverage in Turkey.

Boza, a cereal-based beverage popular in southeast Europe, is fortified with probiotics and is believed to positively impact the composition of the gut microflora. This investigation focused on fermented cereal-based beverage boza to identify strains of probiotic Lactobacillus spp. capable of inhibiting carbohydrate-hydrolysing enzymes α-glucosidase (AG) and α-amylase (AA). The isolated bacterial strains underwent a comprehensive assessment, including biochemical, molecular, and probiotic trait analyses such as tolerance survivability, adhesion, safety, and health-promoting attributes. We evaluated the inhibitory potential of the supernatant, cell lysate, and intact cells of Lactobacillus spp. Molecular analysis has revealed that isolates RAMULAB30 and RAMULAB29 exhibit a significant genetic similarity (>97%) to Lacticaseibacillus paracasei and Limosilactobacillus fermentum, respectively. These findings are documented in the NCBI database. They exhibited significant resistance to gastrointestinal and intestinal fluids, also indicating their potential for adhesion. Additionally, the isolates showed a significant antibacterial activity, particularly against Micrococcus luteus. They showed resistance to vancomycin and methicillin antibiotics but were more susceptible to streptomycin and ampicillin. Furthermore, the strains demonstrated antioxidant properties. To ensure their safety, a haemolytic assay was conducted despite their general recognition as safe (GRAS) status. The study primarily aimed to evaluate the inhibitory effects of the extract on enzymes AG and AA. Bacterial isolates demonstrated a significant inhibitory activity against both enzyme AG (32%-67% inhibition) and enzyme AA (18%-46% inhibition) in different forms, including supernatant (CS), lysed extract (CE), and intact cell (IC). These findings underscore the potential of bacterial isolates to inhibit the enzyme activity effectively. Furthermore, the L. fermentum RAMULAB29 and L. paracasei RAMULAB30 strains exhibit remarkable antidiabetic potential. Food products incorporating these strains have promising prospects as nutraceuticals, providing improved health benefits.

Facial Prior Guided Micro-Expression Generation.

This paper focuses on the facial micro-expression (FME) generation task, which has potential application in enlarging digital FME datasets, thereby alleviating the lack of training data with labels in existing micro-expression datasets. Despite obvious progress in the image animation task, FME generation remains challenging because existing image animation methods can hardly encode subtle and short-term facial motion information. To this end, we present a facial-prior-guided FME generation framework that takes advantage of facial priors for facial motion generation. Specifically, we first estimate the geometric locations of action units (AUs) with detected facial landmarks. We further calculate an adaptive weighted prior (AWP) map, which alleviates the estimation error of AUs while efficiently capturing subtle facial motion patterns. To achieve smooth and realistic synthesis results, we use our proposed facial prior module to guide motion representation and generation modules in mainstream image animation frameworks. Extensive experiments on three benchmark datasets consistently show that our proposed facial prior module can be adopted in image animation frameworks and significantly improve their performance on micro-expression generation. Moreover, we use the generation technique to enlarge existing datasets, thereby improving the performance of general action recognition backbones on the FME recognition task. Our code is available at https://github.com/sysu19351158/FPB-FOMM.

Enhancing 2D Face Recognition Systems: Addressing Yaw Poses and Occlusions With Masks, Glasses, and Both

Biometric identification in general and face recognition in particular are used to solve a great number of tasks, both security-related and related to device authentication. Although research in face recognition is state-of-the-art today, real face recognition systems still have real problems in real environments, for example, the problems of pose variation and occlusion. In particular, the given paper is devoted to the study of the effects of 2D face recognition depending on the yaw angles and occlusions that include masks and glasses or their combination. In this regard, the UPM dataset is employed to compare the face recognition models using MTCNN, FaceNet, SVC, MLP, and the ensemble model with the hard voting mechanism for the final decision. The following will be used in the assessment; accuracy, F1 score, confusion, classification matrix, and ROC curve. These outcomes reveal the variations in the recognition efficiency in the context of different occlusion circumstances, along with prospects and limitations concerning their use.

Causality-Enhanced Multiple Instance Learning with Graph Convolutional Networks for Parkinsonian Freezing-of-Gait Assessment.

Freezing of gait (FoG) is a common disabling symptom of Parkinson's disease (PD). It is clinically characterized by sudden and transient walking interruptions for specific human body parts, and it presents the localization in time and space. Due to the difficulty in extracting global fine-grained features from lengthy videos, developing an automated five-point FoG scoring system is quite challenging. Therefore, we propose a novel video-based automated five-classification FoG assessment method with a causality-enhanced multiple-instance-learning graph convolutional network (GCN). This method involves developing a temporal segmentation GCN to segment each video into three motion stages for stage-level feature modeling, followed by a multiple-instance-learning framework to divide each stage into short clips for instance-level feature extraction. Subsequently, an uncertainty-driven multiple-instance-learning GCN is developed to capture spatial and temporal fine-grained features through GCN scheme and uncertainty learning, respectively, for acquiring global representations. Finally, a causality-enhanced graph generation strategy is proposed to exploit causal inference for mining and enhancing human structures causally related to clinical assessment, thereby extracting spatial causal features. Extensive experimental results demonstrate the excellent performance of the proposed method on five-classification FoG assessment with an accuracy of 62.72% and an acceptable accuracy of 91.32%, which is confirmed by independent testing. Additionally, it enables temporal and spatial localization of FoG events to a certain extent, facilitating reasonable clinical interpretations. In conclusion, our method provides a valuable tool for automated FoG assessment in PD, and the proposed causality-related component exhibits promising potential for extension to other general and medical fine-grained action recognition tasks.

The Development of Chinese Ceramic Painting and Trend

Contemporary ceramic painting has developed over a long period since its inception, from the definition of concepts to the sorting out of theories, and from the extensive participation of artists to the general recognition of peers. This paper summarizes the characteristics of the development of ceramic painting before and after the new century on the basis of combing the development lineage of Chinese ceramic painting during 1979-2019.

Crises of the international legal system and their role in developing principles and norms of international law: Retrospective analysis

The article examines the influence of international legal system crises on the establishment and advancement of generally recognized principles and norms of international law. It is shown that the causes of crisis phenomena in international law can include inconsistency of the norms of international treaties and customs with the proclaimed principles of international law, poor regulation of the critical issues of the world community’s life and its institutions; non-implementation of the enshrined principles because of the lack of political will or imperfection of international legal mechanisms. On the example of the principles of conscientious fulfillment of international obligations, the sovereign equality of states and respect for the rights inherent in sovereignty, non-intervention in the internal affairs of states enshrined in the 1945 United Nations Charter, it is shown how the principles undergo changes in different eras, resulting in shifts in emphasis and enabling the evolution of international legal regulation. The terminological discussions, which have spanned centuries, leading to a wide range of interpretations regarding the fundamental principles and norms of international law, including the concept of general recognition, are considered. It has been concluded that numerous principles of international law were established to address crisis situations in international legal affairs. However, sometimes, these principles can inadvertently exacerbate conflicts, as evidenced by the Europe-America tensions in the 19th century. The primary areas of development for the international law principles are revealed: the alignment of specific principles in different international law branches with generally recognized principles and norms, the interplay between principles across different international law branches, which is crucial for regulating a substantial portion of international legal relations and the consolidation of judicial practice from international justice bodies.

An Analysis of Visual Preference and Characteristics through a Woodland Garden Perception Survey

Background and objective: Woodland gardens, or gardens designed to emulate the aesthetic and environmental characteristics of forest vegetation, can assist in resolving various environmental and societal problems. However, research regarding woodland gardens in a Korean context has been insufficient, as the concept has only recently been introduced to Korea. This study was conducted to investigate the Korean public's perceptions of two types of woodland gardens and to suggest future directions for the popularization of woodland gardens in Korea.Methods: This study was carried out based on a survey. The respondents were provided with a questionnaire on three sets of images representing two types of woodland garden (naturalistic and urban) and a typical formal garden. The questionnaire was designed based on the semantic differential method to gather information on the general public's recognition of the concept of woodland gardens, and their preference and perception of each type of garden. The collected data were analyzed using SPSS Statistics 29.Results: The results suggest that the majority of the respondents were familiar with the term "woodland garden." Of the types of gardens, preference for naturalistic woodland gardens (NWGs) was the highest. Landscape adjectives associated with each type of garden were natural, harmonious, comfortable and simple for NWGs, and organized, artificial, simple, poor, and comfortable for urban woodland gardens (UWGs). A factor analysis on the adjectives identified four factors for each type. Of the identified factors, comfort and stability were found to have particularly greater effects on preference.Conclusion: Preference for NWGs was greater than UWGs, due to the perception that they provided greater comfort and stability. It is expected that designing woodland gardens based on the finding of this study would aid in the popularization of woodland gardens, and the advancement of garden culture in Korea.

Composting Grief Into Light: Building Agentive Healing Literacies with BIPOC Adolescent Writers

Responding to a general recognition that teachers are often ill-prepared to address the intersections of healing, literacy learning, and grief, this paper offers an overview of classroom practices and curricula that support the co-creation of containers of safety for students to explore grief while building academic literacies. Acknowledgment that grief with layers of trauma can often be a subtext of classroom life requires that teachers consider and adopt suitable manners of healing-centered and trauma-informed instruction. Drawing on the voices of students and on fifteen years of experience working with embodiment practices in the classroom, this article provides descriptions of tangible approaches and curricula that organically weave together agentive healing literacies with academic literacies.