Search

Chemokines are cytokines with chemoattractant capacities that exert their physiological functions through the binding of chemokine receptors. Thus, chemokine and receptor complexes exert important roles in regulating development and homeostasis during routine immune surveillance and inflammation. Compared to mammals, the physiology and structure of chemokine receptors in fish have not been systematically studied. Furthermore, the salmonid-specific whole genome duplication has significantly increased the number of functional paralogs of chemokine receptors. In this context, in the current study, trout exhibited 17 cxcr genes, including 12 newly identified and 5 previously identified receptors. Interestingly, gene expression of brain cxcr1 and cxcr4, kidney cxcr3 and cxcr4, and spleen cxcr3, cxcr4, and cxcr5 subtypes were altered by bacterial infection, whereas brain cxcr1, kidney cxcr1 and cxcr7, and liver cxcr2, cxcr3, and cxcr4 subtypes were changed in response to environmental changes. Based on protein structures predicted by ColabFold, the conserved amino acids in binding pockets between trout CXCR4.1 subtypes and human CXCR4 were also analyzed. Our study is valuable from a comparative point of view, providing new insights into the identification and physiology of salmonid chemokine receptors.

The age and mass of red giants are essential for understanding the structure and evolution of the Milky Way. Traditional isochrone methods for these estimations are inherently limited due to overlapping isochrones in the Hertzsprung-Russell diagram, while asteroseismology, though more precise, requires high-precision, long-term observations. In response to these challenges, we developed a novel framework, Spectral Transformer (SPT), to predict the age and mass of red giants aligned with asteroseismology from their spectra. A key component of SPT, the Multi-head Hadamard Self-Attention mechanism, designed specifically for spectra, can capture complex relationships across different wavelength. Further, we introduced a Mahalanobis distance-based loss function to address scale imbalance and interaction mode loss, and incorporated Monte Carlo dropout for quantitative analysis of prediction uncertainty.Trained and tested on 3,880 red giant spectra from LAMOST, the SPT achieved remarkable age and mass estimations with average percentage errors of 17.64% and 6.61%, respectively, and provided uncertainties for each corresponding prediction. The results significantly outperform those of traditional machine learning algorithms and demonstrate a high level of consistency with asteroseismology methods and isochrone fitting techniques. In the future, our work will leverage datasets from the Chinese Space Station Telescope and the Large Synoptic Survey Telescope to enhance the precision of the model and broaden its applicability in the field of astronomy and astrophysics., Comment: Accepted by A&A

Wan-Sen Yan,1,2 Su-Jiao Liu,1 Meng-Meng Liu1 1Department of Psychology, School of Medical Humanitarians, Guizhou Medical University, Guiyang, People’s Republic of China; 2Guizhou Research Institute for Health Development, Guizhou Medical University, Guiyang, People’s Republic of ChinaCorrespondence: Wan-Sen Yan, Department of Psychology, School of Medical Humanitarians, Guizhou Medical University and Guizhou Research Institute for Health Development, Guizhou Medical University, 9 Beijing Road, Yunyan District, Guiyang, 550004, People’s Republic of China, Tel +86-136-4850-4644, Email yanwansen@163.comBackground: Although structured clinical interviews are considered the gold standard for assessing binge eating disorder (BED), the self-administered Binge Eating Scale (BES) has been widely used as a screening tool for BED in clinical research. However, the psychometric properties of the BES among Chinese young adults remain unclear. This study aimed to examine the validity of a Chinese version of the BES with a large sample.Methods: A total of 2182 young adult college students were tested using the Simplified Chinese version of BES (SCBES), the 7-Item Binge-Eating Disorder Screener (BEDS-7), the Zung Self-Rating Depression Scale (SDS), the Generalized Anxiety Disorder Scale (GAD-7), and the Dual-Modes of Self-Control Scale (DMSC). The frequency of objective binge-eating episodes was used as a measure of severity. Validity and reliability of the SCBES were assessed through multiple analyses, along with the item analysis.Results: The data revealed that the SCBES demonstrated reasonable reliability and validity. The Cronbach’s α value was 0.813, with a one-month test–retest reliability of 0.835. The exploratory factor analysis (EFA) extracted three first-order factors, which explained a total of 53.82% of the variance. The confirmatory factor analysis (CFA) confirmed the three-factor model (ie, Binge-eating behaviors, Lack of control, Negative affects related t

Neural algorithmic reasoning is an emerging research direction that endows neural networks with the ability to mimic algorithmic executions step-by-step. A common paradigm in existing designs involves the use of historical embeddings in predicting the results of future execution steps. Our observation in this work is that such historical dependence intrinsically contradicts the Markov nature of algorithmic reasoning tasks. Based on this motivation, we present our ForgetNet, which does not use historical embeddings and thus is consistent with the Markov nature of the tasks. To address challenges in training ForgetNet at early stages, we further introduce G-ForgetNet, which uses a gating mechanism to allow for the selective integration of historical embeddings. Such an enhanced capability provides valuable computational pathways during the model's early training phase. Our extensive experiments, based on the CLRS-30 algorithmic reasoning benchmark, demonstrate that both ForgetNet and G-ForgetNet achieve better generalization capability than existing methods. Furthermore, we investigate the behavior of the gating mechanism, highlighting its degree of alignment with our intuitions and its effectiveness for robust performance., Comment: To appear at ICLR 2024 (Spotlight paper). 17 pages, 10 figures

The ever-expanding scale of integrated circuits has brought about a significant rise in the design risks associated with radiation-resistant integrated circuit chips. Traditional single-particle experimental methods, with their iterative design approach, are increasingly ill-suited for the challenges posed by large-scale integrated circuits. In response, this article introduces a novel sensitivity-aware single-particle radiation effects simulation framework tailored for System-on-Chip platforms. Based on SVM algorithm we have implemented fast finding and classification of sensitive circuit nodes. Additionally, the methodology automates soft error analysis across the entire software stack. The study includes practical experiments focusing on RISC-V architecture, encompassing core components, buses, and memory systems. It culminates in the establishment of databases for Single Event Upsets (SEU) and Single Event Transients (SET), showcasing the practical efficacy of the proposed methodology in addressing radiation-induced challenges at the scale of contemporary integrated circuits. Experimental results have shown up to 12.78X speed-up on the basis of achieving 94.58% accuracy., Comment: Accepted to the 61th ACM/IEEE Design Automation conference (DAC 2024)

Sarcasm Explanation in Dialogue (SED) is a new yet challenging task, which aims to generate a natural language explanation for the given sarcastic dialogue that involves multiple modalities (i.e., utterance, video, and audio). Although existing studies have achieved great success based on the generative pretrained language model BART, they overlook exploiting the sentiments residing in the utterance, video and audio, which are vital clues for sarcasm explanation. In fact, it is non-trivial to incorporate sentiments for boosting SED performance, due to three main challenges: 1) diverse effects of utterance tokens on sentiments; 2) gap between video-audio sentiment signals and the embedding space of BART; and 3) various relations among utterances, utterance sentiments, and video-audio sentiments. To tackle these challenges, we propose a novel sEntiment-enhanceD Graph-based multimodal sarcasm Explanation framework, named EDGE. In particular, we first propose a lexicon-guided utterance sentiment inference module, where a heuristic utterance sentiment refinement strategy is devised. We then develop a module named Joint Cross Attention-based Sentiment Inference (JCA-SI) by extending the multimodal sentiment analysis model JCA to derive the joint sentiment label for each video-audio clip. Thereafter, we devise a context-sentiment graph to comprehensively model the semantic relations among the utterances, utterance sentiments, and video-audio sentiments, to facilitate sarcasm explanation generation. Extensive experiments on the publicly released dataset WITS verify the superiority of our model over cutting-edge methods.

In recent years, with the rapid development of computer information technology, the development of artificial intelligence has been accelerating. The traditional geometry recognition technology is relatively backward and the recognition rate is low. In the face of massive information database, the traditional algorithm model inevitably has the problems of low recognition accuracy and poor performance. Deep learning theory has gradually become a very important part of machine learning. The implementation of convolutional neural network (CNN) reduces the difficulty of graphics generation algorithm. In this paper, using the advantages of lenet-5 architecture sharing weights and feature extraction and classification, the proposed geometric pattern recognition algorithm model is faster in the training data set. By constructing the shared feature parameters of the algorithm model, the cross-entropy loss function is used in the recognition process to improve the generalization of the model and improve the average recognition accuracy of the test data set., Comment: 6 pages,9 figures

Some two decades ago, Dörnyei (2005) proposed that motivation for L2 learning could be modelled as a self-system. Despite the profound influence of Dörnyei’s scholarship and impact of the L2 Motivational Self System (L2MSS) model, the fundamental premise that motivation for L2 learning can constitute a self-system has escaped critical scrutiny. Highlighting how the self-system constitutes a framework within which self-referential cognition is organized, and that self-appraisal occurs in relation to socially-derived standards (Bandura, 1978; Higgins, 1990), this article critically assesses the utility of a self-system conceptualization. This is accomplished by addressing five problem areas connected with the L2MSS and which relate to the model’s self-system conceptualization: the “fantasy problem” (nondifferentiation of desire and fantasy), the “ought-to L2 self problem” (unspecificity of relevant others and internalization processes), the “integrativeness problem” (difficulty of incorporating affiliation motives), the “learning experience problem” (failure to account for relational and biographical influences), and the “context problem” (inadequate modelling of learner–environment interactions). Critical engagement with these problem areas demonstrates how the self-system conceptualization embodied in the L2MSS is tightly circumscribed, and how a self-regulatory system framework can provide greater utility., CC BY 4.0

This paper studies about the continues growth of national economy and innovation of science and technology the level of construction and development of China's artificial intelligence field has made a qualitative leap. The reasonable application of artificial intelligence technology is the most important and indispensable key element of the modern media integration process, which can not only maximize the role of the media in the social scope of communication functions, but also effectively give the advantages of diversified media communication, realize the real time interactive communication between the media and the market users, and comprehensively enhance the core competitiveness of mainstream media.This essay will future analyze and discuss the use of artificial intelligence technology in media convergence, aiming to provide scientific reference opinions for the same industry in China.

In recent years, the scientific community has called for improvements in the credibility, robustness and reproducibility of research, characterized by increased interest and promotion of open and transparent research practices. While progress has been positive, there is a lack of consideration about how this approach can be embedded into undergraduate and postgraduate research training. Specifically, a critical overview of the literature which investigates how integrating open and reproducible science may influence student outcomes is needed. In this paper, we provide the first critical review of literature surrounding the integration of open and reproducible scholarship into teaching and learning and its associated outcomes in students. Our review highlighted how embedding open and reproducible scholarship appears to be associated with (i) students' scientific literacies (i.e. students' understanding of open research, consumption of science and the development of transferable skills); (ii) student engagement (i.e. motivation and engagement with learning, collaboration and engagement in open research) and (iii) students' attitudes towards science (i.e. trust in science and confidence in research findings). However, our review also identified a need for more robust and rigorous methods within pedagogical research, including more interventional and experimental evaluations of teaching practice. We discuss implications for teaching and learning scholarship.

Yi Zhou,1 Weina Gao,2 Shumin Gao,2 Xutong Guo,2 Meng Liu,2 Congjie Cao1 1School of Nursing, Langfang Health Vocational College, Langfang, Hebei, People’s Republic of China; 2Department of Orthopedics, Baoding No.1 Central Hospital, Baoding, Hebei, People’s Republic of ChinaCorrespondence: Weina Gao, Department of Orthopedics, Baoding No.1 Central Hospital, No. 320, Changcheng North Street, Lianchi District, Baoding, Hebei, 071000, People’s Republic of China, Tel/Fax +86 312-5975023, Email gaoweina984926@163.comPurpose: To examine whether exercise self-efficacy mediates the contributions of pain catastrophizing and kinesiophobia to exercise adherence in patients after total knee arthroplasty.Patients and Methods: A cross-sectional study design was conducted. A total 211 post-total knee arthroplasty patients were recruited from three orthopedics units of a tertiary hospital in China. Participants were invited to complete questionnaires on pain catastrophizing, kinesiophobia, exercise self-efficacy, and exercise adherence. Mplus 8.3 software was used to construct mediation models.Results: Pain catastrophizing and kinesiophobia were negatively correlated with exercise adherence (r = − 0.509, r = − 0.605, p < 0.001 respectively), while exercise self-efficacy were positively associated with exercise adherence (r = 0.799, p < 0.001). The results found exercise self-efficacy mediated the correlations of pain catastrophizing and kinesiophobia with exercise adherence after adjusting for demographic and clinical covariates. Pain catastrophizing indirectly affected patients’ exercise adherence through its effect on exercise efficacy (indirect effect: − 0.412), while Kinesiophobia is directly associated with exercise adherence and also indirectly through exercise self-efficacy (direct effect: − 0.184, indirect effect: − 0.415).Conclusion: Patients after total knee arthroplasty who have high levels of psychological distress (pain catastrophizing and kinesi

Si Liu,1,2 Xiao-yun Xiong,2 Hua Chen,1 Meng-die Liu,1 Ying Wang,1 Ying Yang,1 Mei-jun Zhang,1 Qin Xiang1 1School of Nursing, Nan Chang University, Nan Chang, Jiang Xi, People’s Republic of China; 2Nursing Department, the Second Affiliated Hospital of Nan Chang University, Nan Chang, Jiang Xi, People’s Republic of ChinaCorrespondence: Xiao-yun Xiong, Nursing Department, the Second Affiliated Hospital of Nan Chang University, Min de Road &num;, Nan Chang, 330006, People’s Republic of China, Tel +86-791-8627-4550, Email 1028970010@qq.comObjective: The purpose of this study was to clarify the concept of transitional care in patients with heart failure.Background: Transitional care is increasingly being applied in patients with heart failure, but the concept of transitional care in heart failure patients is not uniform and confused with other definitions, which limits further research and practice on transitional care for these patients.Design: Rodgers’ evolutionary concept analysis.Methods: A comprehensive literature search was conducted using the PUBMED, EMBASE, EBSCO, Chinese Biological Medicine (CBM), CNKI, and WANFANG databases (up to January 26, 2023). We used Rodgers’ evolutionary concept analysis method to identify related concepts, attributes, antecedents, and consequences of transitional care in patients with heart failure.Results: A total of 33 articles were included. The following attributes belonging to transitional care in patients with heart failure were extracted from the literature: self-care, multidisciplinary collaboration, and information transmission. The antecedents were patients’ health status, the health literacy of patients and caregivers, the role functions of the main implementer and social and medical resources. Consequences were separated into two categories: patient-centered health outcomes (all-cause mortality, health-related quality of life, discharge preparedness, self-care behaviors, satisfaction of patients) and healthca

Background: RNA splicing plays significant roles in fundamental biological activities. However, our knowledge about the roles of alternative splicing and underlying mechanisms during spermatogenesis is limited. Results: Here, we report that Serine/arginine-rich splicing factor 2 (SRSF2), also known as SC35, plays critical roles in alternative splicing and male reproduction. Male germ cell-specific deletion of Srsf2 by Stra8-Cre caused complete infertility and defective spermatogenesis. Further analyses revealed that deletion of Srsf2 disrupted differentiation and meiosis initiation of spermatogonia. Mechanistically, by combining RNA-seq data with LACE-seq data, we showed that SRSF2 regulatory networks play critical roles in several major events including reproductive development, spermatogenesis, meiotic cell cycle, synapse organization, DNA recombination, chromosome segregation, and male sex differentiation. Furthermore, SRSF2 affected expression and alternative splicing of Stra8, Stag3 and Atr encoding critical factors for spermatogenesis in a direct manner. Conclusions: Taken together, our results demonstrate that SRSF2 has important functions in spermatogenesis and male fertility by regulating alternative splicing. © 2023, BioMed Central Ltd., part of Springer Nature.

Shuang Xu,1 Yi Fu,2 Dan Xu,1 Shuang Han,1 Mingzhi Wu,3 Xinrong Ju,1 Meng Liu,1 De-Sheng Huang,4,5 Peng Guan4,6 1Library of China Medical University, Shenyang, Liaoning, People’s Republic of China; 2School of Health Management, China Medical University, Shenyang, Liaoning, People’s Republic of China; 3Library of Shenyang Pharmaceutical University, Shenyang, Liaoning, People’s Republic of China; 4Key Laboratory of Environmental Stress and Chronic Disease Control & Prevention (China Medical University), Ministry of Education, Shenyang, Liaoning, People’s Republic of China; 5Department of Intelligent Computing, School of Intelligent Medicine, China Medical University, Shenyang, Liaoning, People’s Republic of China; 6Department of Epidemiology, School of Public Health, China Medical University, Shenyang, Liaoning, People’s Republic of ChinaCorrespondence: De-Sheng Huang; Peng Guan, China Medical University, Shenyang, Liaoning, 110122, People’s Republic of China, Email dshuang@cmu.edu.cn; pguan@cmu.edu.cnBackground: Before the COVID-19 pandemic, tuberculosis is the leading cause of death from a single infectious agent worldwide for the past 30 years. Progress in the control of tuberculosis has been undermined by the emergence of multidrug-resistant tuberculosis. The aim of the study is to reveal the trends of research on medications for multidrug-resistant pulmonary tuberculosis (MDR-PTB) through a novel method of bibliometrics that co-occurs specific semantic Medical Subject Headings (MeSH).Methods: PubMed was used to identify the original publications related to medications for MDR-PTB. An R package for text mining of PubMed, pubMR, was adopted to extract data and construct the co-occurrence matrix-specific semantic types. Biclustering analysis of high-frequency MeSH term co-occurrence matrix was performed by gCLUTO. Scientific knowledge maps were constructed by VOSviewer to create overlay visualization and density visualization. Burst detection was pe

Very metal-poor (VMP, [Fe/H]<-2.0) stars offer a wealth of information on the nature and evolution of elemental production in the early galaxy and universe. The upcoming China Space Station Telescope (CSST) will provide us with a large amount of spectroscopic data that may contain plenty of VMP stars, and thus it is crucial to determine the stellar atmospheric parameters ($T_{eff}$, $\log g$, and [Fe/H]) for low-resolution spectra similar to the CSST spectra (R~200). In this paper, a two-dimensional Convolutional Neural Network (CNN) model with three convolutional layers and two fully connected layers is constructed. The principal aim of this work is to measure the ability of this model to estimate stellar parameters on low-resolution (R~200) spectra and to identify VMP stars so that we can better search for VMP stars in the spectra observed by CSST.We mainly use 10,008 observed spectra of VMP stars from LAMOST DR3, and 16,638 spectra of common stars ([Fe/H]>-2.0) from LAMOST DR8 for the experiment and make comparisons. All spectra are reduced to R~200 to match the resolution of the CSST and are preprocessed and collapsed into two-dimensional spectra for input to the CNN model. The results show that the MAE values are 99.40 K for $T_{eff}$, 0.22 dex for $\log g$, 0.14 dex for [Fe/H], and 0.26 dex for [C/Fe], respectively. Besides, the CNN model efficiently identifies VMP stars with a precision of 94.77%. The validation and practicality of this model are also tested on the MARCS synthetic spectra. This paper powerfully demonstrates the effectiveness of the proposed CNN model in estimating stellar parameters for low-resolution spectra (R~200) and recognizing VMP stars that are of interest for stellar population and galactic evolution work., Comment: 13 pages, 9 figures

Imaging Science Subsystem (ISS) mounted on the Cassini spacecraft has taken a lot of images, which provides an important source of high-precision astrometry of some planets and satellites. However, some of these images are degraded by trailed stars. Previously, these degraded images cannot be used for astrometry. In this paper, a new method is proposed to detect and compute the centers of these trailed stars automatically. The method is then performed on the astrometry of ISS images with trailed stars. Finally, we provided 658 astrometric positions between 2004 and 2017 of several satellites that include Enceladus, Dione, Tethys, Mimas and Rhea. Compared with the JPL ephemeris SAT427, the mean residuals of these measurements are 0.11 km and 0.26 km in right ascension and declination, respectively. Their standard deviations are 1.08 km and 1.37 km, respectively. The results show that the proposed method performs astrometric measurements of Cassini ISS images with trailed stars effectively.

The emergence of large-scale replication projects yielding successful rates substantially lower than expected caused the behavioural, cognitive, and social sciences to experience a so-called ‘replication crisis’. In this Perspective, we reframe this ‘crisis’ through the lens of a credibility revolution, focusing on positive structural, procedural and community-driven changes. Second, we outline a path to expand ongoing advances and improvements. The credibility revolution has been an impetus to several substantive changes which will have a positive, long-term impact on our research environment.

In recent years, the scientific community has called for improvements in the credibility, robustness and reproducibility of research, characterized by increased interest and promotion of open and transparent research practices. While progress has been positive, there is a lack of consideration about how this approach can be embedded into undergraduate and postgraduate research training. Specifically, a critical overview of the literature which investigates how integrating open and reproducible science may influence student outcomes is needed. In this paper, we provide the first critical review of literature surrounding the integration of open and reproducible scholarship into teaching and learning and its associated outcomes in students. Our review highlighted how embedding open and reproducible scholarship appears to be associated with (i) students' scientific literacies (i.e. students’ understanding of open research, consumption of science and the development of transferable skills); (ii) student engagement (i.e. motivation and engagement with learning, collaboration and engagement in open research) and (iii) students' attitudes towards science (i.e. trust in science and confidence in research findings). However, our review also identified a need for more robust and rigorous methods within pedagogical research, including more interventional and experimental evaluations of teaching practice. We discuss implications for teaching and learning scholarship.

Visual speech (i.e., lip motion) is highly related to auditory speech due to the co-occurrence and synchronization in speech production. This paper investigates this correlation and proposes a cross-modal speech co-learning paradigm. The primary motivation of our cross-modal co-learning method is modeling one modality aided by exploiting knowledge from another modality. Specifically, two cross-modal boosters are introduced based on an audio-visual pseudo-siamese structure to learn the modality-transformed correlation. Inside each booster, a max-feature-map embedded Transformer variant is proposed for modality alignment and enhanced feature generation. The network is co-learned both from scratch and with pretrained models. Experimental results on the LRSLip3, GridLip, LomGridLip, and VoxLip datasets demonstrate that our proposed method achieves 60% and 20% average relative performance improvement over independently trained audio-only/visual-only and baseline fusion systems, respectively.

Temporal graph learning aims to generate high-quality representations for graph-based tasks with dynamic information, which has recently garnered increasing attention. In contrast to static graphs, temporal graphs are typically organized as node interaction sequences over continuous time rather than an adjacency matrix. Most temporal graph learning methods model current interactions by incorporating historical neighborhood. However, such methods only consider first-order temporal information while disregarding crucial high-order structural information, resulting in suboptimal performance. To address this issue, we propose a self-supervised method called S2T for temporal graph learning, which extracts both temporal and structural information to learn more informative node representations. Notably, the initial node representations combine first-order temporal and high-order structural information differently to calculate two conditional intensities. An alignment loss is then introduced to optimize the node representations, narrowing the gap between the two intensities and making them more informative. Concretely, in addition to modeling temporal information using historical neighbor sequences, we further consider structural knowledge at both local and global levels. At the local level, we generate structural intensity by aggregating features from high-order neighbor sequences. At the global level, a global representation is generated based on all nodes to adjust the structural intensity according to the active statuses on different nodes. Extensive experiments demonstrate that the proposed model S2T achieves at most 10.13% performance improvement compared with the state-of-the-art competitors on several datasets.

Meng Liu,1,&ast; Xinyi Liu,1,&ast; Yuqian Wang,1 Ziyang Wang,1 Huihui Tuo,1 Yiguo Feng,2 Yan Zheng1 1Department of Dermatology, the First Affiliated Hospital of Xi’an Jiaotong University, Xi’an, People’s Republic of China; 2Department of Dermatology, the Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Yiguo Feng, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an, People’s Republic of China, Email fengyiguo70@163.com Yan Zheng, The First Affiliated Hospital of Xi’an Jiaotong University, Xi’an, People’s Republic of China, Email zenyan66@126.comBackground: Epidermal cysts are common benign epithelial tumors. They are known to result from penetrating-type injuries or infection of human papillomavirus. The differential diagnosis commonly includes multiplex steatocystoma, lipoma, and neurofibroma. Pathological examination is essential for diagnosis, and surgical excision is the recommended treatment.Objective: We report a case in a man who presented with a cystic lesion on the scalp over 22 years to provide clinical evidence for mechanism of epidermal cysts. We conducted epidemiological analysis of 3949 patients with epidermal cysts to clarify the epidemiological characteristics and clinical features of epidermal cysts.Patients and Methods: A total of 3949 individuals with confirmed epidermal cysts were collected for analysis. Data were expressed as mean ± SEM and analyzed using Student’s t-test.Results: Our data showed that the mean age of diagnosis of males was statistically earlier than that of females (P< 0.001), but no significant difference in sex predilection was observed (P=0.55). The high incidence age of males and females was in the young and middle stage. Lesion locations were a bit different among age groups, but the face was the most common site of epidermal cyst at all age stages.Conclusion: O

In recent years, frequent natural or man-made disturbances have accelerated the study of resilience management. As an important source of system resilience, maintenance activities need to be managed effectively. Meanwhile, importance measures have become an effective tool in maintenance management. However, there are still some challenges in the studies of importance measure-based maintenance management. A comprehensive review and discussion can serve as a useful reference for the future research. This paper firstly reviews the definitions of importance measures, maintenance, and resilience and then examines their interrelationships. It then analyses the roles of importance measures in maintenance management for resilience improvement. Finally, it proposes future research directions

Federated Learning (FL) offers collaborative model training without data sharing but is vulnerable to backdoor attacks, where poisoned model weights lead to compromised system integrity. Existing countermeasures, primarily based on anomaly detection, are prone to erroneous rejections of normal weights while accepting poisoned ones, largely due to shortcomings in quantifying similarities among client models. Furthermore, other defenses demonstrate effectiveness only when dealing with a limited number of malicious clients, typically fewer than 10%. To alleviate these vulnerabilities, we present G$^2$uardFL, a protective framework that reinterprets the identification of malicious clients as an attributed graph clustering problem, thus safeguarding FL systems. Specifically, this framework employs a client graph clustering approach to identify malicious clients and integrates an adaptive mechanism to amplify the discrepancy between the aggregated model and the poisoned ones, effectively eliminating embedded backdoors. We also conduct a theoretical analysis of convergence to confirm that G$^2$uardFL does not affect the convergence of FL systems. Through empirical evaluation, comparing G$^2$uardFL with cutting-edge defenses, such as FLAME (USENIX Security 2022) [28] and DeepSight (NDSS 2022) [36], against various backdoor attacks including 3DFed (SP 2023) [20], our results demonstrate its significant effectiveness in mitigating backdoor attacks while having a negligible impact on the aggregated model's performance on benign samples (i.e., the primary task performance). For instance, in an FL system with 25% malicious clients, G$^2$uardFL reduces the attack success rate to 10.61%, while maintaining a primary task performance of 73.05% on the CIFAR-10 dataset. This surpasses the performance of the best-performing baseline, which merely achieves a primary task performance of 19.54%., Comment: 19 pages, 7 figures

Temporal graph clustering (TGC) is a crucial task in temporal graph learning. Its focus is on node clustering on temporal graphs, and it offers greater flexibility for large-scale graph structures due to the mechanism of temporal graph methods. However, the development of TGC is currently constrained by a significant problem: the lack of suitable and reliable large-scale temporal graph datasets to evaluate clustering performance. In other words, most existing temporal graph datasets are in small sizes, and even large-scale datasets contain only a limited number of available node labels. It makes evaluating models for large-scale temporal graph clustering challenging. To address this challenge, we build arXiv4TGC, a set of novel academic datasets (including arXivAI, arXivCS, arXivMath, arXivPhy, and arXivLarge) for large-scale temporal graph clustering. In particular, the largest dataset, arXivLarge, contains 1.3 million labeled available nodes and 10 million temporal edges. We further compare the clustering performance with typical temporal graph learning models on both previous classic temporal graph datasets and the new datasets proposed in this paper. The clustering performance on arXiv4TGC can be more apparent for evaluating different models, resulting in higher clustering confidence and more suitable for large-scale temporal graph clustering. The arXiv4TGC datasets are publicly available at: https://github.com/MGitHubL/arXiv4TGC.

We tackle the problem of graph out-of-distribution (OOD) generalization. Existing graph OOD algorithms either rely on restricted assumptions or fail to exploit environment information in training data. In this work, we propose to simultaneously incorporate label and environment causal independence (LECI) to fully make use of label and environment information, thereby addressing the challenges faced by prior methods on identifying causal and invariant subgraphs. We further develop an adversarial training strategy to jointly optimize these two properties for causal subgraph discovery with theoretical guarantees. Extensive experiments and analysis show that LECI significantly outperforms prior methods on both synthetic and real-world datasets, establishing LECI as a practical and effective solution for graph OOD generalization. Our code is available at https://github.com/divelab/LECI.

Inductive relation reasoning for knowledge graphs, aiming to infer missing links between brand-new entities, has drawn increasing attention. The models developed based on Graph Inductive Learning, called GraIL-based models, have shown promising potential for this task. However, the uni-directional message-passing mechanism hinders such models from exploiting hidden mutual relations between entities in directed graphs. Besides, the enclosing subgraph extraction in most GraIL-based models restricts the model from extracting enough discriminative information for reasoning. Consequently, the expressive ability of these models is limited. To address the problems, we propose a novel GraIL-based inductive relation reasoning model, termed MINES, by introducing a Message Intercommunication mechanism on the Neighbor-Enhanced Subgraph. Concretely, the message intercommunication mechanism is designed to capture the omitted hidden mutual information. It introduces bi-directed information interactions between connected entities by inserting an undirected/bi-directed GCN layer between uni-directed RGCN layers. Moreover, inspired by the success of involving more neighbors in other graph-based tasks, we extend the neighborhood area beyond the enclosing subgraph to enhance the information collection for inductive relation reasoning. Extensive experiments on twelve inductive benchmark datasets demonstrate that our MINES outperforms existing state-of-the-art models, and show the effectiveness of our intercommunication mechanism and reasoning on the neighbor-enhanced subgraph., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Ground-state 3D geometries of molecules are essential for many molecular analysis tasks. Modern quantum mechanical methods can compute accurate 3D geometries but are computationally prohibitive. Currently, an efficient alternative to computing ground-state 3D molecular geometries from 2D graphs is lacking. Here, we propose a novel deep learning framework to predict 3D geometries from molecular graphs. To this end, we develop an equilibrium message passing neural network (EMPNN) to better capture ground-state geometries from molecular graphs. To provide a testbed for 3D molecular geometry analysis, we develop a benchmark that includes a large-scale molecular geometry dataset, data splits, and evaluation protocols. Experimental results show that EMPNN can efficiently predict more accurate ground-state 3D geometries than RDKit and other deep learning methods. Results also show that the proposed framework outperforms self-supervised learning methods on property prediction tasks.

Deep graph clustering has recently received significant attention due to its ability to enhance the representation learning capabilities of models in unsupervised scenarios. Nevertheless, deep clustering for temporal graphs, which could capture crucial dynamic interaction information, has not been fully explored. It means that in many clustering-oriented real-world scenarios, temporal graphs can only be processed as static graphs. This not only causes the loss of dynamic information but also triggers huge computational consumption. To solve the problem, we propose a general framework for deep Temporal Graph Clustering called TGC, which introduces deep clustering techniques to suit the interaction sequence-based batch-processing pattern of temporal graphs. In addition, we discuss differences between temporal graph clustering and static graph clustering from several levels. To verify the superiority of the proposed framework TGC, we conduct extensive experiments. The experimental results show that temporal graph clustering enables more flexibility in finding a balance between time and space requirements, and our framework can effectively improve the performance of existing temporal graph learning methods. The code is released: https://github.com/MGitHubL/Deep-Temporal-Graph-Clustering.

Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches another) but ignores the higher-order neighbor relations (i.e., a matching structure among multiple data samples). Re-ranking, a popular post-processing practice, has revealed the superiority of capturing neighbor relations in single-modality retrieval tasks. However, it is ineffective to directly extend existing re-ranking algorithms to image-text retrieval. In this paper, we analyze the reason from four perspectives, i.e., generalization, flexibility, sparsity, and asymmetry, and propose a novel learnable pillar-based re-ranking paradigm. Concretely, we first select top-ranked intra- and inter-modal neighbors as pillars, and then reconstruct data samples with the neighbor relations between them and the pillars. In this way, each sample can be mapped into a multimodal pillar space only using similarities, ensuring generalization. After that, we design a neighbor-aware graph reasoning module to flexibly exploit the relations and excavate the sparse positive items within a neighborhood. We also present a structure alignment constraint to promote cross-modal collaboration and align the asymmetric modalities. On top of various base backbones, we carry out extensive experiments on two benchmark datasets, i.e., Flickr30K and MS-COCO, demonstrating the effectiveness, superiority, generalization, and transferability of our proposed re-ranking paradigm., Comment: Accepted by SIGIR'2023

Few-shot relation reasoning on knowledge graphs (FS-KGR) aims to infer long-tail data-poor relations, which has drawn increasing attention these years due to its practicalities. The pre-training of previous methods needs to manually construct the meta-relation set, leading to numerous labor costs. Self-supervised learning (SSL) is treated as a solution to tackle the issue, but still at an early stage for FS-KGR task. Moreover, most of the existing methods ignore leveraging the beneficial information from aliasing relations (AR), i.e., data-rich relations with similar contextual semantics to the target data-poor relation. Therefore, we proposed a novel Self-Supervised Learning model by leveraging Aliasing Relations to assist FS-KGR, termed SARF. Concretely, four main components are designed in our model, i.e., SSL reasoning module, AR-assisted mechanism, fusion module, and scoring function. We first generate the representation of the co-occurrence patterns in a generative manner. Meanwhile, the representations of aliasing relations are learned to enhance reasoning in the AR-assist mechanism. Besides, multiple strategies, i.e., simple summation and learnable fusion, are offered for representation fusion. Finally, the generated representation is used for scoring. Extensive experiments on three few-shot benchmarks demonstrate that SARF achieves state-of-the-art performance compared with other methods in most cases., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Ziyang Wang,1,2 Meng Liu,1,2 Hao Lei,1,2 Panpan Lei,3 Xinyi Liu,1,2 Jing Zhang,1,2 Shengxiang Xiao,2 Yan Zheng,1,2 Yi-Guo Feng2 1Department of Dermatology, the First Affiliated Hospital of Xi’an Jiaotong University, Xi’an, People’s Republic of China; 2Department of Dermatology, the Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an, People’s Republic of China; 3Center for Mitochondrial Biology and Medicine, The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Xi’an Jiaotong University School of Life Science and Technology, Xi’an, People’s Republic of ChinaCorrespondence: Yi-Guo Feng, Department of Dermatology, the Second Affiliated Hospital of Xi’an Jiaotong University, School of Medicine, Xi’an, 730070, People’s Republic of China, Email fengyiguo70@163.comBackground: Eruptive syringoma (ES) is a clinical variant of the appendageal tumor syringoma. Around 75% of ES arise in the head or neck, which makes them unsightly. ES is common in patients with amyloidosis, diabetes, and Down’s syndrome, suggesting that it may be associated with potential systemic effects. ES is a rare tumor with the unclear pathogenesis and no effective treatment.Methods: A PubMed search of ES was conducted. Plasma samples of patients with ES were acquired from the Department of Dermatology at Xi’an Jiaotong University’s Second Affiliated Hospital. After removing highly abundant proteins, plasma samples were subjected to proteomics and metabolomics analysis using liquid chromatography-tandem mass spectrometry (LC-MS/MS).Results: LC-MS/MS revealed 71 differentially expressed proteins and 18 differentially abundant metabolites. The functional analysis highlighted the importance of complement binding, coagulation, secretory granules and vesicle lumen. Further, the study revealed 15 hub genes associated with FGG, GC, APOE, FGA, FGB, C4A, C3, CRP, C4B, FLNA, TAGLN2, ANXA5, MYL6, MYL12B, and TLN1 organized into three clusters. Th

Low-surface-brightness galaxies (LSBGs), fainter members of the galaxy population, are thought to be numerous. However, due to their low surface brightness, the search for a wide-area sample of LSBGs is difficult, which in turn limits our ability to fully understand the formation and evolution of galaxies as well as galaxy relationships. Edge-on LSBGs, due to their unique orientation, offer an excellent opportunity to study galaxy structure and galaxy components. In this work, we utilize the You Only Look Once object detection algorithm to construct an edge-on LSBG detection model by training on 281 edge-on LSBGs in Sloan Digital Sky Survey (SDSS) $gri$-band composite images. This model achieved a recall of 94.64% and a purity of 95.38% on the test set. We searched across 938,046 $gri$-band images from SDSS Data Release 16 and found 52,293 candidate LSBGs. To enhance the purity of the candidate LSBGs and reduce contamination, we employed the Deep Support Vector Data Description algorithm to identify anomalies within the candidate samples. Ultimately, we compiled a catalog containing 40,759 edge-on LSBG candidates. This sample has similar characteristics to the training data set, mainly composed of blue edge-on LSBG candidates. The catalog is available online at https://github.com/worldoutside/Edge-on_LSBG., Comment: 12 pages, 11 figures, accepted to be published on APJS

Wan-Sen Yan,1,2 Meng-Meng Liu,1 Su-Jiao Liu1 1Department of Psychology, School of Medical Humanitarians, Guizhou Medical University, Guiyang, People’s Republic of China; 2Guizhou Research Institute for Health Development, Guizhou Medical University, Guiyang, People’s Republic of ChinaCorrespondence: Wan-Sen Yan, Department of Psychology, School of Medical Humanitarians, Guizhou Medical University, 9 Beijing Road, Yunyan District, Guiyang, 550004, People’s Republic of China, Tel +86-136-4850-4644, Email yanwansen@163.comBackground: Similar to addictive disorders, deficits on cognitive control might be involved in the onset and development of Binge Eating Disorder (BED). However, it remains unclear whether general or food-related inhibitory control impairments would be basically linked to overeating and binge eating behaviors. This study thus aimed to investigate behavioral performance and electrophysiological correlates of food-related inhibitory control among individuals with binge eating behavior.Methods: Sixty individuals with probable BED (pBED) and 60 well-matched healthy controls (HCs) were assessed using the typical Stop-Signal Task, a revised Go/No Go Task, and a food-related Go/No Go Task. Besides, another separate sample, including 35 individuals with pBED and 35 HCs, completed the food-related Go/No Go Task when EEG signals were recorded with the event-related potentials (ERPs).Results: The data revealed that the pBED group performed worse with a longer SSRT on the Stop-Signal Task compared with HCs (Cohen’s d = 0.58, p = 0.002). Moreover, on the food-related Go/No Go Task, the pBED group had a lower success rate of inhibition in no-go trials (Cohen’s d = 0.47, p = 0.012). The ERPs data showed that in comparison with HCs, the pBED group exhibited increased P300 latency (FC1, FC2, F3, F4, FZ) in the no-go trials of the food-related Go/No Go Task (Cohen’s d 0.56– 0.73, all p < 0.05).Conclusion: These findings suggested that individuals with

In contrast to conventional visual question answering, video-grounded dialog necessitates a profound understanding of both dialog history and video content for accurate response generation. Despite commendable progress made by existing approaches, they still face the challenges of incrementally understanding complex dialog history and assimilating video information. In response to these challenges, we present an iterative search and reasoning framework, which consists of a textual encoder, a visual encoder, and a generator. Specifically, we devise a path search and aggregation strategy in the textual encoder, mining core cues from dialog history that are pivotal to understanding the posed questions. Concurrently, our visual encoder harnesses an iterative reasoning network to extract and emphasize critical visual markers from videos, enhancing the depth of visual comprehension. Finally, we utilize the pre-trained GPT-2 model as our answer generator to decode the mined hidden clues into coherent and contextualized answers. Extensive experiments on three public datasets demonstrate the effectiveness and generalizability of our proposed framework.

Cardiac magnetic resonance imaging (CMR) has emerged as a valuable diagnostic tool for cardiac diseases. However, a limitation of CMR is its slow imaging speed, which causes patient discomfort and introduces artifacts in the images. There has been growing interest in deep learning-based CMR imaging algorithms that can reconstruct high-quality images from highly under-sampled k-space data. However, the development of deep learning methods requires large training datasets, which have not been publicly available for CMR. To address this gap, we released a dataset that includes multi-contrast, multi-view, multi-slice and multi-coil CMR imaging data from 300 subjects. Imaging studies include cardiac cine and mapping sequences. Manual segmentations of the myocardium and chambers of all the subjects are also provided within the dataset. Scripts of state-of-the-art reconstruction algorithms were also provided as a point of reference. Our aim is to facilitate the advancement of state-of-the-art CMR image reconstruction by introducing standardized evaluation criteria and making the dataset freely accessible to the research community. Researchers can access the dataset at https://www.synapse.org/#!Synapse:syn51471091/wiki/., Comment: 14 pages, 8 figures

In this paper, we present a novel problem, namely video timeline modeling. Our objective is to create a video-associated timeline from a set of videos related to a specific topic, thereby facilitating the content and structure understanding of the story being told. This problem has significant potential in various real-world applications, for instance, news story summarization. To bootstrap research in this area, we curate a realistic benchmark dataset, YouTube-News-Timeline, consisting of over $12$k timelines and $300$k YouTube news videos. Additionally, we propose a set of quantitative metrics to comprehensively evaluate and compare methodologies. With such a testbed, we further develop and benchmark several deep learning approaches to tackling this problem. We anticipate that this exploratory work will pave the way for further research in video timeline modeling. The assets are available via https://github.com/google-research/google-research/tree/master/video_timeline_modeling., Comment: Accepted as a spotlight by NeurIPS 2023, Track on Datasets and Benchmarks

Audiovisual data is everywhere in this digital age, which raises higher requirements for the deep learning models developed on them. To well handle the information of the multi-modal data is the key to a better audiovisual modal. We observe that these audiovisual data naturally have temporal attributes, such as the time information for each frame in the video. More concretely, such data is inherently multi-modal according to both audio and visual cues, which proceed in a strict chronological order. It indicates that temporal information is important in multi-modal acoustic event modeling for both intra- and inter-modal. However, existing methods deal with each modal feature independently and simply fuse them together, which neglects the mining of temporal relation and thus leads to sub-optimal performance. With this motivation, we propose a Temporal Multi-modal graph learning method for Acoustic event Classification, called TMac, by modeling such temporal information via graph learning techniques. In particular, we construct a temporal graph for each acoustic event, dividing its audio data and video data into multiple segments. Each segment can be considered as a node, and the temporal relationships between nodes can be considered as timestamps on their edges. In this case, we can smoothly capture the dynamic information in intra-modal and inter-modal. Several experiments are conducted to demonstrate TMac outperforms other SOTA models in performance. Our code is available at https://github.com/MGitHubL/TMac., Comment: This work has been accepted by ACM MM 2023 for publication

Sentiment analysis is a crucial task that aims to understand people's emotional states and predict emotional categories based on multimodal information. It consists of several subtasks, such as emotion recognition in conversation (ERC), aspect-based sentiment analysis (ABSA), and multimodal sentiment analysis (MSA). However, unifying all subtasks in sentiment analysis presents numerous challenges, including modality alignment, unified input/output forms, and dataset bias. To address these challenges, we propose a Task-Specific Prompt method to jointly model subtasks and introduce a multimodal generative framework called UniSA. Additionally, we organize the benchmark datasets of main subtasks into a new Sentiment Analysis Evaluation benchmark, SAEval. We design novel pre-training tasks and training methods to enable the model to learn generic sentiment knowledge among subtasks to improve the model's multimodal sentiment perception ability. Our experimental results show that UniSA performs comparably to the state-of-the-art on all subtasks and generalizes well to various subtasks in sentiment analysis., Comment: Accepted to ACM MM 2023

Deep graph clustering, which aims to group nodes into disjoint clusters by neural networks in an unsupervised manner, has attracted great attention in recent years. Although the performance has been largely improved, the excellent performance of the existing methods heavily relies on an accurately predefined cluster number, which is not always available in the real-world scenario. To enable the deep graph clustering algorithms to work without the guidance of the predefined cluster number, we propose a new deep graph clustering method termed Reinforcement Graph Clustering (RGC). In our proposed method, cluster number determination and unsupervised representation learning are unified into a uniform framework by the reinforcement learning mechanism. Concretely, the discriminative node representations are first learned with the contrastive pretext task. Then, to capture the clustering state accurately with both local and global information in the graph, both node and cluster states are considered. Subsequently, at each state, the qualities of different cluster numbers are evaluated by the quality network, and the greedy action is executed to determine the cluster number. In order to conduct feedback actions, the clustering-oriented reward function is proposed to enhance the cohesion of the same clusters and separate the different clusters. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method. The source code of RGC is shared at https://github.com/yueliu1999/RGC and a collection (papers, codes and, datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering on Github.

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This work aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.

Multimodal knowledge graphs (MKGs), which intuitively organize information in various modalities, can benefit multiple practical downstream tasks, such as recommendation systems, and visual question answering. However, most MKGs are still far from complete, which motivates the flourishing of MKG reasoning models. Recently, with the development of general artificial architectures, the pretrained transformer models have drawn increasing attention, especially for multimodal scenarios. However, the research of multimodal pretrained transformer (MPT) for knowledge graph reasoning (KGR) is still at an early stage. As the biggest difference between MKG and other multimodal data, the rich structural information underlying the MKG still cannot be fully leveraged in existing MPT models. Most of them only utilize the graph structure as a retrieval map for matching images and texts connected with the same entity. This manner hinders their reasoning performances. To this end, we propose the graph Structure Guided Multimodal Pretrained Transformer for knowledge graph reasoning, termed SGMPT. Specifically, the graph structure encoder is adopted for structural feature encoding. Then, a structure-guided fusion module with two different strategies, i.e., weighted summation and alignment constraint, is first designed to inject the structural information into both the textual and visual features. To the best of our knowledge, SGMPT is the first MPT model for multimodal KGR, which mines the structural information underlying the knowledge graph. Extensive experiments on FB15k-237-IMG and WN18-IMG, demonstrate that our SGMPT outperforms existing state-of-the-art models, and prove the effectiveness of the designed strategies., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessed

Supervised machine learning approaches have been increasingly used in accelerating electronic structure prediction as surrogates of first-principle computational methods, such as density functional theory (DFT). While numerous quantum chemistry datasets focus on chemical properties and atomic forces, the ability to achieve accurate and efficient prediction of the Hamiltonian matrix is highly desired, as it is the most important and fundamental physical quantity that determines the quantum states of physical systems and chemical properties. In this work, we generate a new Quantum Hamiltonian dataset, named as QH9, to provide precise Hamiltonian matrices for 999 or 2998 molecular dynamics trajectories and 130,831 stable molecular geometries, based on the QM9 dataset. By designing benchmark tasks with various molecules, we show that current machine learning models have the capacity to predict Hamiltonian matrices for arbitrary molecules. Both the QH9 dataset and the baseline models are provided to the community through an open-source benchmark, which can be highly valuable for developing machine learning methods and accelerating molecular and materials design for scientific and technological applications. Our benchmark is publicly available at https://github.com/divelab/AIRS/tree/main/OpenDFT/QHBench., Comment: Accepted by NeurIPS 2023, Track on Datasets and Benchmarks

Video moment localization, also known as video moment retrieval, aiming to search a target segment within a video described by a given natural language query. Beyond the task of temporal action localization whereby the target actions are pre-defined, video moment retrieval can query arbitrary complex activities. In this survey paper, we aim to present a comprehensive review of existing video moment localization techniques, including supervised, weakly supervised, and unsupervised ones. We also review the datasets available for video moment localization and group results of related work. In addition, we discuss promising future directions for this field, in particular large-scale datasets and interpretable video moment localization models.

We study graph data augmentation by mixup, which has been used successfully on images. A key operation of mixup is to compute a convex combination of a pair of inputs. This operation is straightforward for grid-like data, such as images, but challenging for graph data. The key difficulty lies in the fact that different graphs typically have different numbers of nodes, and thus there lacks a node-level correspondence between graphs. In this work, we propose S-Mixup, a simple yet effective mixup method for graph classification by soft alignments. Specifically, given a pair of graphs, we explicitly obtain node-level correspondence via computing a soft assignment matrix to match the nodes between two graphs. Based on the soft assignments, we transform the adjacency and node feature matrices of one graph, so that the transformed graph is aligned with the other graph. In this way, any pair of graphs can be mixed directly to generate an augmented graph. We conduct systematic experiments to show that S-Mixup can improve the performance and generalization of graph neural networks (GNNs) on various graph classification tasks. In addition, we show that S-Mixup can increase the robustness of GNNs against noisy labels.

Zeolite-encapsulated metal clusters have been shown to be an effective bifunctional catalyst for tandem catalysis. Nevertheless, the efficient encapsulation of nanometric metal species into a high-aluminum ZSM-5 zeolite still poses a significant challenge. In this contribution, we have prepared well-dispersed and ultra-small Ru clusters encapsulated within a high-aluminum ZSM-5 zeolite (with a Si/Al ratio of ∼30-40) via an in situ two-stage hydrothermal synthesis method. Small Ru clusters with an average size of ∼1 nm have been identified by scanning transmission electron microscopy and hydrogen chemisorption. Shape-selective hydrogenation experiments with different probe molecules reveal a predominant encapsulation (∼90%) of metal clusters within the MFI zeolite cavities, which significantly enhances thermal stability of metal clusters against sintering. 27Al magic angle spinning nuclear magnetic resonance and Brønsted acid site (BAS) titration experiments show the successful incorporation of aluminum species (>99%) into the zeolite framework and build-up of intimacy between the Ru clusters and BASs at a sub-nanometric level. The resulting Ru@H-ZSM-5 shows an enhanced activity and stability for the crucial hydrodeoxygenation (HDO) of phenol to cyclohexane, in biomass valorization. This synthesis strategy could be of great help for the rational design and development of zeolitic bifunctional catalysts and could be extended to other crystalline porous materials.