Search

Most human synthesis schemes use high-performance servers, so the user interaction experience of mobile devices is not satisfied. Viewing human synthesis results on smartphones directly increases user interaction and enhances user experience. This paper proposes a smart frame selection network (SFSN) on mobile devices to reduce the traffic between smartphones and cloud. We leverage the attention and relationship model to focus on the relationship between a single frame and the entire video, which can better select important frames, thus reducing the traffic and computing effectively. In addition, we build a multi-task human synthesis system based on SFSN to process the generation tasks such as background changing, pose transfer and virtual try-on in a unified framework. Evaluation results indicate proposed approach reduces the number of frames to be processed by more than 42.2%. [ABSTRACT FROM AUTHOR]

The purpose of this study was to investigate the impact of mLearning or mobile device practice on the attention and accuracy of student's use of math concepts, specifically, telling time. A single subject, alternating treatment design was used to compare mLearning to paper and pencil practice in four 3rd grade male students. Results were mixed; two children were observed to be more on-task during the mLearning practice, and two children were observed to perform similarly across both conditions. Additionally, two children performed similarly on correctly completed problems across both conditions, and two children performed better using paper and pencil practice. All students completed more math problems during the paper and pencil practice. [ABSTRACT FROM AUTHOR]

Retracted papers often circulate widely on social media, digital news, and other websites before their official retraction. The spread of potentially inaccurate or misleading results from retracted papers can harm the scientific community and the public. Here, we quantify the amount and type of attention 3,851 retracted papers received over time in different online platforms. Comparingwith a set of nonretracted control papers fromthe same journals with similar publication year, number of coauthors, and author impact, we show that retracted papers receive more attention after publication not only on social media but also, on heavily curated platforms, such as news outlets and knowledge repositories, amplifying the negative impact on the public. At the same time, we find that posts on Twitter tend to express more criticism about retracted than about control papers, suggesting that criticism-expressing tweets could contain factual information about problematic papers. Most importantly, around the time they are retracted, papers generate discussions that are primarily about the retraction incident rather than about research findings, showing that by this point, papers have exhausted attention to their results and highlighting the limited effect of retractions. Our findings reveal the extent to which retracted papers are discussed on different online platforms and identify at scale audience criticism toward them. In this context, we show that retraction is not an effective tool to reduce online attention to problematic papers. [ABSTRACT FROM AUTHOR]

Objectives: With mounting evidence on health risks caused by e-cigarette consumption, it is of great necessity to explore not only smokers' but also nonsmokers' responses to e-cigarette marketing messages, such as online commercials. Employing both psychophysiological and self-report measures, this study examined nonsmoking young adults' cognitive, emotional, and attitudinal reactions to two major message features used in e-cigarette commercials: argument quantity and endorsement type. Method: The experiment used a 2 (endorsement type: celebrity and average citizen) × 2 (argument quantity: low and high) × 2 (message repetition) within-subjects design. Continuous heart rate (indicative of attention) and skin conductance activity (indicative of emotional arousal) were measured during ads viewing. Self-reported ad liking and vaping urge were assessed immediately after participants finished watching each commercial. Results: Results showed that compared to high argument quantity, low argument quantity elicited more attention, evoked higher emotional arousal, and generated stronger ad liking and vaping urge. Additionally, compared to average-citizen endorsement, the presence of celebrity endorsement elicited higher attention and lower emotional arousal in nonsmoking young adults. There was a significant interaction effect of endorsement type and argument quantity on ad liking. Conclusions: For nonsmoking young adults, low argument quantity commercials might have the greatest impact in initiating vaping behavior, which has implications for regulatory policies regarding e-cigarette. Celebrity endorsement was effective in catching nonsmokers' attention but had limited effects on emotional involvement and product adoption. The implications of the findings were finally discussed in more details in the manuscript. [ABSTRACT FROM AUTHOR]

With the explosion in the number of papers being generated, it has become a common practice to recommend papers related to research interests of authors. Existing methods mainly focus on using binary author–paper interactions to mine the research interests of authors. However, sparse binary interactions make it extremely difficult to distinguish the authors' research interests. This results in an inability to find papers that authors need. Generally, the research interests of coauthors are highly correlated and this is useful in broadening the distinctions between authors' research interests. Therefore, we propose a new ternary coauthor recommendation (TCRec) method for paper recommendation. Specifically, we construct a coauthor ternary to describe the coauthorship between authors to explore potential ternary interactions. First, an attention-based bidirectional long short-term memory (Bi-LSTM) is built to learn title and abstract information to represent the research area of a paper and accordingly initialize the research interests for each author. Then, an academic heterogeneous graph with a dual attention mechanism is designed to aggregate the semantic information of neighboring nodes and metapaths. This mechanism can be employed to aggregate the relationships between authors and papers in the academic network to describe the research interests for authors. Finally, after constructing the ternary, a multilayer perceptron (MLP) is applied to mine potential associations between the ternary to enrich author–paper interactions for paper recommendation. Extensive experimental results from two real academic datasets not only show the superior performance of our model over state-of-the-art approaches but also demonstrate its potential value for paper recommendation. [ABSTRACT FROM AUTHOR]

The papers in this issue provide an excellent example of how pertinent distinctions which emerge from analysis of significant data sets can be communicated to colleagues and used to make sense of observations. The distinctions are vividly described, illustrated and exemplified, and used to chart maturation in student use of examples from middle school, through high school and into university. Curiously, no corresponding maturation was detected in students' choice of examples to use for themselves. Contrast was detected between the way students used the same examples for comprehending a conjecture and testing its validity, and the way that some mathematicians used specifically constructed examples for locating underlying structure. What emerged for me from reading these papers is confirmation of the central role of attention, the productiveness of engaging students at the earliest ages and throughout their schooling with the detection and expression of generality, and the importance of being explicit about the scope of generality encompassed by a claim. Purposeful use of examples by students could be expected to develop as teachers explicitly use examples purposefully with and for students. A reasonable conjecture might be that getting students to be explicit about the scope of generality, of possible variation of which they are aware, might shed light on obstacles and barriers to reasoning which might otherwise lead to proof. [ABSTRACT FROM AUTHOR]

This article explores the factors influencing the future citations of conference papers. We concentrated on the explanatory power of early attention on conference papers for citations collected from Google Scholar and Scopus. The early attention data includes users' online activities in a conference support system: CN3. Bookmarks from the bibliographic management system, Citeulike, were used as a collateral source of early attention. To examine the chronological contributions of 13 factors on citations, a multiple sequential regression analysis was conducted for three timepoints of the publication cycle—paper submission, time of conferences, and months after conferences. Our results illustrate that online readers' early attention of Citeulike bookmarks were found to have the most influence on the future impact of the conference papers. The early attention records from CN3 made noteworthy improvements to explaining both the Google and Scopus citations as well. We also found that the type of papers the number of papers presented at a conference, and the best article award records were significant factors influencing future citations. However, the magnitude of the effects made by online readers' early attention from both sources appears to be larger than these three traditional factors. [ABSTRACT FROM AUTHOR]

Previous studies revealed that performance in paper-and-pencil tests of attention, such as the d2-R test, improves with practice, though the sources of these practice effects are yet unknown. Practice effects in psychometric tests are a serious problem because they impede the evaluation of test performance and constrain the utility of these tests. This study addresses the role of target-specific learning for practice in a d2-like paper-and-pencil test of attention. Two variants of a d2-like test, which exclusively differed in the set of target stimuli, were constructed. Participants were tested on two days separated by one week. Participants in the control condition searched for the same targets (among the same distractors) in each session, whereas participants in the test group searched for different targets (among the same distractors) in each session. Results showed practice benefits in both groups, but benefits were larger in the control group than in the test group. The results suggest that practice improves the processing of target features in paper-and-pencil tests of attention. Hence, using two versions with different sets of targets may effectively reduce practice effects in d2-like tests of attention. Further implications of the findings are discussed. [ABSTRACT FROM AUTHOR]

Purpose: The use of brand slogans that represent brand concepts on app launch pages can improve user brand impressions. The purpose of this paper is to investigate the impact of using animated or static spokes-characters with brand slogans on app launch pages. Design/methodology/approach: Using the theory of attention selection, the authors conducted two experiments to study the boundary and mediation path of the influence of the motion attributes of spokes-characters (static vs animated) on brand memory based on app launch time (3 s vs 5 s), user engagement with spokes-characters and the level of attention to brand slogans. Findings: Study 1 explores the effect of the interaction between launch time and the motion attributes of spokes-characters on brand memory. The results show that when the launch time of the app is 3 s, the advertisement memory effect of using a static spokes-character is better than that of using an animated spokes-character; when the launch time of the app is 5 s, the advertisement memory effect of using an animated spokes-character is better than that of using a static spokes-character. Study 2 shows that user engagement with spokes-characters and the level of attention given to brand slogans play a continuous mediating role in the effect of the interaction between launch time and the motion attributes of spokes-characters on brand memory. Originality/value: This paper contributes to the marketing literature by expanding the knowledge of spokes-characters and animated visual images, providing new insights for future research. [ABSTRACT FROM AUTHOR]

Segmenting clouds and their shadows is a critical challenge in remote sensing image processing. The shape, texture, lighting conditions, and background of clouds and their shadows impact the effectiveness of cloud detection. Currently, architectures that maintain high resolution throughout the entire information-extraction process are rapidly emerging. This parallel architecture, combining high and low resolutions, produces detailed high-resolution representations, enhancing segmentation prediction accuracy. This paper continues the parallel architecture of high and low resolution. When handling high- and low-resolution images, this paper employs a hybrid approach combining the Transformer and CNN models. This method facilitates interaction between the two models, enabling the extraction of both semantic and spatial details from the images. To address the challenge of inadequate fusion and significant information loss between high- and low-resolution images, this paper introduces a method based on ASMA (Axial Sharing Mixed Attention). This approach establishes pixel-level dependencies between high-resolution and low-resolution images, aiming to enhance the efficiency of image fusion. In addition, to enhance the effective focus on critical information in remote sensing images, the AGM (Attention Guide Module) is introduced, to integrate attention elements from original features into ASMA, to alleviate the problem of insufficient channel modeling of the self-attention mechanism. Our experimental results on the Cloud and Cloud Shadow dataset, the SPARCS dataset, and the CSWV dataset demonstrate the effectiveness of our method, surpassing the state-of-the-art techniques for cloud and cloud shadow segmentation. [ABSTRACT FROM AUTHOR]

There is a growing body of scholarship on the ethics of autonomous vehicles. Yet the ethical discourse has mostly been focusing on the behavior of the vehicle in accident scenarios. This paper offers a different ethical prism: the implications of the autonomous vehicle for human well-being. As such, it contributes to the growing discourse on the wider societal and moral implications of the autonomous vehicle. The paper is premised on the neo-Aristotelian approach which holds that as human beings, our well-being depends on developing and exercising our innate human capacities: to know, understand, love, be sociable, imagine, create and use our bodies and use our willpower. To develop and exercise these capacities, our environments need to provide a range of opportunities which will trigger the development and exercise of the capacities. The main argument advanced in the paper is that one plausible future of the autonomous vehicle—a future of single-rider autonomous vehicles—may effectively reduce the opportunities to develop and exercise our capacities to know, be sociable and use our willpower. It will therefore be bad for human well-being, and this provides us with a moral reason to resist this plausible future and search for alternative ones. [ABSTRACT FROM AUTHOR]

This paper develops a version of the acquaintance theory of introspective justification. In the process, it rejects the view that acquaintance is sui generic in favor of a view that identifies acquaintance with availability for selection by attention mechanisms. Moreover, unlike many recent accounts of knowledge by acquaintance, it explains the epistemic significance of acquaintance in terms of the epistemic basing relation without any need to appeal to the structure or existence of phenomenal concepts. Lastly, while in ideal cases acquaintance will provide a kind of infallible justification, the paper shows how to extend these ideas to allow that acquaintance can provide fallible introspective justification. [ABSTRACT FROM AUTHOR]

Introduction: Subclinical hypothyroidism is an endocrine disorder that can adversely affect cognitive performance. In this regard, patients with subclinical hypothyroidism may develop poor attention. However, the effects of this endocrine disorder on auditory attention is unclear. This study aims to evaluate the impact of subclinical hypothyroidism on auditory divided attention. Materials and Methods: This cross-sectional, case control study was performed on 30 adult patients, aged 20-40 years, who met the study inclusion criteria. Based on their Thyroid Stimulating Hormone (TSH) level, the subjects were divided into two case groups (each with 15 patients) with a TSH level of 5˂TSH≤10 and 10˂TSH≤15. A healthy control group was recruited with matched age, sex, and education with the case groups. The participants were evaluated by the Persian version of the Bergen dichotic listening test. Among different experimental situations that included non-forced attention, forced right, and forced left, we chose the non-forced attention. Statistical analysis was done in SPSS V. 25. Results: There was a significant difference between the subclinical hypothyroid (5˂TSH≤10 group) and controls in the scores of the right and left ear. However, there was no significant difference between scores of right and left ear in subclinical hypothyroid (10˂TSH≤15 group). No significant difference in scores of the right and left ear was found between men and women in three groups. Conclusion: Subclinical hypothyroidism had no effect on auditory divided attention. [ABSTRACT FROM AUTHOR]

Abstract: In school, at least in the US, we were taught to multiply by hand according to a standard algorithm. Most people find that algorithm difficult to use, and many children fail to learn it. We propose a new way to make sense of this difficulty: to treat explicit computation as perceptually supported physical and mental action. Based on recent work in neuroscience, we trace the flow of arithmetic information to emphasize demands on visual working memory and attention. We predict that algorithms that make moderate demands on memory and attention will work better than others that make stronger demands. We suggest that the judicious use of spatial schemas can reduce such cognitive demands. Experimental evidence from children in an inner-city school supports this claim. Our work suggests new ways to think about instruction. The goal should be to minimize demands that present obstacles and maximize instead what human eyes, bodies, and brains do well. [Copyright &y& Elsevier]

This paper presents a conceptual framework for the intellectual virtues in the context of online search. Intellectual virtues are dispositions and skills that enable good thinking and wise reasoning, such as intellectual humility and attentiveness. Despite their importance, today the intellectual virtues tend to be underdeveloped across society. In light of the institutional role that online search plays in life today, there is an opportunity (perhaps an obligation) for online search to facilitate the development of intellectual virtue. The framework presented in this paper locates this development in three areas: the Searcher, the System, and Society. Major issues in information ethics and virtue epistemology are discussed for each of these areas, leading to recommendations for education, design, and research. This paper provides specific suggestions in this regard along with an agenda for future research at the intersection of ethics, epistemology, and online search. [ABSTRACT FROM AUTHOR]

• Volitional signals for gaze control provided by multiple parallel pathways to the superior colliculus (88) • Interaction of sensory task-related signals within the multi-layered superior colliculus (79) • Convergence of bottom-up (world statistics) and top-down (goal and task) signals in the SC for gaze control (91) • Models of attention such as saliency map and their physiological basis (60) • Cerebral and subcortical inputs to control output signals for gaze in the SC (64) Volitional signals for gaze control are provided by multiple parallel pathways converging on the midbrain superior colliculus (SC), whose deeper layers output to the brainstem gaze circuits. In the first of two papers (Takahashi and Veale, 2023), we described the properties of gaze behavior of several species under both laboratory and natural conditions, as well as the current understanding of the brainstem and spinal cord circuits implementing gaze control in primate. In this paper, we review the parallel pathways by which sensory and task information reaches SC and how these sensory and task signals interact within SC's multilayered structure. This includes both bottom-up (world statistics) signals mediated by sensory cortex, association cortex, and subcortical structures, as well as top-down (goal and task) influences which arrive via either direct excitatory pathways from cerebral cortex, or via indirect basal ganglia relays resulting in inhibition or dis-inhibition as appropriate for alternative behaviors. Models of attention such as saliency maps serve as convenient frameworks to organize our understanding of both the separate computations of each neural pathway, as well as the interaction between the multiple parallel pathways influencing gaze. While the spatial interactions between gaze's neural pathways are relatively well understood, the temporal interactions between and within pathways will be an important area of future study, requiring both improved technical methods for measurement and improvement of our understanding of how temporal dynamics results in the observed spatiotemporal allocation of gaze. [ABSTRACT FROM AUTHOR]

The layout and configuration of urban infrastructure are essential for the orderly operation and healthy development of cities. With the promotion and popularization of new energy vehicles, the modeling and prediction of charging pile usage and allocation have garnered significant attention from governments and enterprises. Short-term demand forecasting for charging piles is crucial for their efficient operation. However, existing prediction models lack a discussion on the appropriate time window, resulting in limitations in station-level predictions. Recognizing the temporal nature of charging pile occupancy, this paper proposes a novel stacked-LSTM model called attention-SLSTM that integrates an attention mechanism to predict the charging demand of electric vehicles at the station level over the next few hours. To evaluate its performance, this paper compares it with several methods. The experimental results demonstrate that the attention-SLSTM model outperforms both LSTM and stacked-LSTM models. Deep learning methods generally outperform traditional time series forecasting methods. In the test set, MAE is 1.6860, RMSE is 2.5040, and MAPE is 9.7680%. Compared to the stacked-LSTM model, MAE and RMSE are reduced by 4.7%and 5%, respectively; while MAPE value decreases by 1.3%, making it superior to LSTM overall. Furthermore, subsequent experiments compare prediction performance among different charging stations, which confirms that the attention-SLSTM model exhibits excellent predictive capabilities within a six-step (2 h) window. [ABSTRACT FROM AUTHOR]

Scientific skepticism about attention has run deeply for a century. We are said to not know what attention is despite over 45 000 scientific papers published on attention since 1950. The theory of attention is shown to be logically inconsistent. Since too many things are said to be attention, the theory faces a dilemma: contradiction or confusion. Empirical methodology provides a solution, entailing a common conception of attention: attention is a subject mentally selecting a target to guide response. The common conception provides a methodological norm yielding a functional structure built into every attentional paradigm, so something we all accept and thereby know. The common conception unifies empirical work into an explanatory theory. Attention is typically what we are trying to explain (effect) and is not an explainer (cause). Attention is one of the most thoroughly investigated psychological phenomena, yet skepticism about attention is widespread: we do not know what it is, it is too many things, there is no such thing. The deficiencies highlighted are not about experimental work but the adequacy of the scientific theory of attention. Combining common scientific claims about attention into a single theory leads to internal inconsistency. This paper demonstrates that a specific functional conception of attention is incorporated into the tasks used in standard experimental paradigms. In accepting these paradigms as valid probes of attention, we commit to this common conception. The conception unifies work at multiple levels of analysis into a coherent scientific explanation of attention. Thus, we all know what attention is. [ABSTRACT FROM AUTHOR]

This paper explores the challenge of establishing a meaningful connection between a neurotypical therapist and a neurodiverse patient who inhabit different Umwelts, that is, perceptual worlds.1 It discusses how addressing anxiety is crucial in preventing communication difficulties from escalating for individuals with autism who may have heightened stress due to an overgrown amygdala. Embodied mirroring is introduced to focus on perceptions and reduce stress. Furthermore, the potential for epigenetic changes due to unaddressed anxiety is raised. The paper emphasises the importance of responding to individual differences in sensory and perceptual experiences to promote effective communication and positive outcomes in therapy. [ABSTRACT FROM AUTHOR]

Person re-identification, as an essential research direction in intelligent security, has gained the focus of researchers and scholars. In practical scenarios, visible light cameras depend highly on lighting conditions and have limited detection capability in poor light. Therefore, many scholars have gradually shifted their research goals to cross-modality person re-identification. However, there are few relevant studies, and challenges remain in resolving the differences in the images of different modalities. In order to solve these problems, this paper will use the research method based on the attention mechanism to narrow the difference between the two modes and guide the network in a more appropriate direction to improve the recognition performance of the network. Aiming at the problem of using the attention mechanism method can improve training efficiency. However, it is easy to cause the model training instability. This paper proposes a cross-modal pedestrian re-recognition method based on the attention mechanism. A new attention mechanism module is designed to allow the network to use less time to focus on more critical features of a person. In addition, a cross-modality hard center triplet loss is designed to supervise the model training better. The paper has conducted extensive experiments on the above two methods on two publicly available datasets, which obtained better performance than similar current methods and verified the effectiveness and feasibility of the proposed methods in this paper. [ABSTRACT FROM AUTHOR]

Perception is, at least sometimes, something we do. This paper is concerned with how to account for perceptual agency (i.e., the active aspect of perception). Eilan divides accounts of perceptual agency up into two camps: enactivist theories hold that perceptual agency is accounted for by the involvement of bodily action, while mental theories hold that perceptual agency is accounted for by the involvement of mental action in perception. In Structuring Mind (2017), Sebastian Watzl aligns his 'activity view' with the mental action route and develops the view that the mental activity of attending infuses perceptual experience with agency. Moreover, Watzl claims that his view can accommodate enactivist intuitions, while rejecting their claims about embodiment. In this paper, we scrutinize the relevant notion of mental action involved in the mental action route. We analyze the involvement of the body in overt acts of attention (like sniffing and smelling) and argue that a constitutively embodied account of mental action provides a better analysis of overt attention than a conjunctive account in which overt attention involves a bodily and a (separate) mental action. Furthermore, we argue that the standard cases of covert attention (such as the Posner paradigm) involve the body in multiple ways. In closing, we discuss the relevance of our analysis for the debate on perceptual agency and the embodied mind thesis. We conclude that the embodied mental action route to theorizing perceptual agency provides the best analysis of perceptual agency but comes with significant commitments about the embodiment of attention. [ABSTRACT FROM AUTHOR]

Accurate power load prediction is an important guide for power system planning and operation. High‐ or low‐load prediction results will affect the operation of the power system. In recent years, deep learning technology represented by convolution neural network (CNN) and transformer has been proved to be suitable for power load prediction. This paper proposes a new short‐term power load hybrid forecasting model, called channel enhanced attention (CEA) and temporal convolutional network (TCN)‐based transformer comprehensive forecasting model. This method combines the short‐term feature extraction ability of TCN with the long‐term dependent capture ability of transformer for short‐term load forecasting. And the CEA designed in this study is added to improve the prediction accuracy. On the same dataset, the designed model predicts power load mean square errors of 0.056 and 0.146 for the next 24 h and the next week, respectively, which is 0.002 to 0.073 and 0.012 to 0.024 lower than the baseline model. The experimental results show that the hybrid short‐term power load prediction model proposed in this paper is significantly better than the existing methods. The predicted curve is in agreement with the actual charge change, which provides a good guidance for short‐term power load prediction. [ABSTRACT FROM AUTHOR]

This paper proposes an positional encoding-based attention mechanism model which can quantify the temporal correlation of ship maneuvering motion to predict the future ship motion in real sea state. To represent the temporal information of the sequential motion status, the positional encoding consisted by sine and cosine functions of different frequencies is chosen as the input of the model. First, the reasonableness of the improved architecture of the model is validated on the standard turning test datasets of an unmanned surface vehicle. Then, the absolute positional encoding based-scaled-dot product attention mechanism model is compared with other two attention mechanism models with different positional encoding and attention calculation methods and its superiority is verified. As demonstrated by exhaustive experiments, the model has the highest prediction accuracy when the input sequence length equals the output sequence length and the accuracy defined in this paper of the model will drop to less than 90% when the predicted length exceeds 45. Finally, the attention mechanism model is compared with the LSTM model with different lengths of input sequences to demonstrate that the attention mechanism model has a faster training speed when dealing with long sequences. [ABSTRACT FROM AUTHOR]

Presently, a significant number of students enrolled in colleges and universities encounter mental health challenges, including academic stress and difficulties in interpersonal relationships. These factors contribute to a decline in mental well-being and necessitate prompt intervention and assistance. The automation of mental health identification in students greatly benefits from the implementation of intelligent emotion recognition systems. Through the analysis of students' emotional states, educational institutions can gain a deeper understanding of students' mental well-being, enabling them to promptly identify and address any issues and offer more complete care and support to students. This paper proposes a method for automated emotion recognition that is driven by data. The method is developed based on the provided background information. The proposed approach incorporates a feature fusion mechanism and an attention mechanism into the ResNet-34 model. This integration enhances the model's capability to analyze intricate details and subsequently improves its classification performance when applied to electroencephalography (EEG) signals. This paper introduces several key innovations. First, an optimization technique is applied to the input component of the model, enabling multifeature fusion. Second, an attention mechanism is incorporated after the residual network module, enabling the model to prioritize parts that contribute to classification and enhance feature extraction. Finally, the network parameters are optimized using both softmax loss and center loss functions. The findings from the analysis of the sentiment EEG public data SJTU Emotion EEG Dataset (SEED) indicate that the proposed sentiment recognition approach not only enhances the classification performance of the model on the sentiment EEG data but also improves the stability of the results. This paper presents a novel approach that enables automatic and efficient recognition of students' emotions on commonly used platforms. The findings of this study hold significant implications for mental health assessment and detection in real-life production settings, offering substantial reference value in this domain. [ABSTRACT FROM AUTHOR]

Preschool children's attention, engagement, and communication during readings from comparable electronic and paper storybooks, and their recall of story content were assessed. Seventy-nine preschoolers listened to one story on a tablet and another in paper format. The e-book contained multimedia and interactive features that activated story-related information. Dependent measures were attention to the book, the adult, and off-task; engagement and communication; recall of story content. Language and executive functioning were assessed. Results showed that (1) the e-book took twice as long to complete, (2) children were more attentive to, and engaged in the e-book, (3) children communicated more about the device during the e-book but more about the story during the paper book, (4) there was no difference in recall by format, (5) executive functioning was a stronger predictor of attention and story recall than was age. Results were discussed in relation to the cognitive theory of multimedia learning. [ABSTRACT FROM AUTHOR]

As the subject of research excellence has received increasing attention (in science policy) over the past few decades, increasing numbers of bibliometric studies have been published dealing with excellent papers. However, many different methods have been used in these studies to identify excellent papers. The present quantitative analysis of the literature has been carried out to acquire an overview of these methods and an indication of an ‘average’ or ‘most frequent’ bibliometric practice. The search in the Web of Science yielded 321 papers dealing with ‘highly cited’, ‘most cited’, ‘top cited’, and ‘most frequently cited’. Of the 321 papers, 16 could not be used in this study. In around 80% of the papers analyzed in this study, a quantitative definition has been provided to identify excellent papers. With definitions that relate to an absolute number, either a certain number of top cited papers (58%) or papers with a minimum number of citations are selected (17%). Approximately 23% worked with percentile rank classes. Over these papers, there is an arithmetic average of the top 7.6% (arithmetic average) or of the top 3% (median). The top 1% is used most frequently in the papers, followed by the top 10%. With the thresholds presented in this study, in future, it will be possible to identify excellent papers based on an ‘average’ or ‘most frequent’ practice among bibliometricians. [ABSTRACT FROM PUBLISHER]

Non-intrusive experimentation and measurements can be obtained from the latest neuroscience scanning techniques and technologies. Such technologies are now quite affordable and could possibly be used for the reading process research in information and communication sciences. The research experiment focuses on measuring the changes in attention while reading the text on different media (devices). The pilot experiment showed that cheap and easy to use brainwave measuring devices can be used for testing reading processes by measuring attention (concentration). The results revealed that a reading medium (device) affects the level of attention and suggested that less attention is needed to read from paper compared to any size or type of screen. Reading books (in a foreign language) can mostly be considered neutral on the attention level scale (slightly shifted towards 53 on a 1-100 scale). [ABSTRACT FROM AUTHOR]

When I fiddle with my hair, or adjust my posture, it is plausible that these activities fall well below my cognitive radar. Some have argued that these are examples of ‘sub‐intentional actions’, actions which are not intentional under any description at all. If true, they are direct counterexamples to the dominant view on which the difference between actions and other events is their intentionality. In this paper, I argue that the case for sub‐intentional actions fails. Firstly, I show that the main argument for the sub‐intentionality of these actions has a structural fault. Secondly, I argue that two apparently natural ways to remedy this fail. Thirdly, I argue that one of the main arguments for thinking of the phenomena as actions undermines thinking of them as sub‐intentional. Finally, I argue that a natural defensive move for the defender of sub‐intentional actions actually undermines the theoretical significance of the view. Ultimately, my aim is to show that although the case for sub‐intentional actions seemed both simple and compelling, it is in fact deeply troubled. [ABSTRACT FROM AUTHOR]

Age-invariant face recognition (AIFR) is a significant research task in general face recognition, and it aims at eliminating gradual discordance of individual's facial appearance caused by aging process. Previous discriminative methods decompose facial components over one-dimensional feature vectors which overlooks critical facial information and hypothesize linear relationships over aging process which is inadequate to describe complex correlations. In this paper, we propose an enhanced AIFR model, namely age-invariant face network (AFN), to eliminate the discrepancy of aging process over facial semblance. Specifically, we propose attentive factorization module (AFM) leveraging attention mechanism to decompose facial features into identity-related features and age-related features in two-dimensional space on both local and contextual levels. We take both linear and nonlinear correlation analyses into account for a better reflection of aging/rejuvenation process and hence propose a hybrid correlation regularizer (HCR) to supervise the decorrelation between factorized features. Both identity features and age features are supervised simultaneously in a multi-task learning framework where only identity features are used in test phase for evaluation of AIFR performance. Experiments across common cross-age datasets (e.g., FG-Net, CACD-VS, CALFW, AgeDB-30) show the effectiveness of proposed AFN. Further, our proposed AFN is validated over LFW dataset to demonstrate its effectiveness on general face recognition task. [ABSTRACT FROM AUTHOR]

Deep neural network (DNN) architectures such as recurrent neural networks and transformers display outstanding performance in modeling sequential unstructured data. However, little is known about their merit to model customer churn with time-varying data. The paper provides a comprehensive evaluation of the ability of recurrent neural networks and transformers for customer churn prediction (CCP) using time-varying behavioral features in the form of recency, frequency, and monetary value (RFM). RFM variables are the backbone of CCP and, more generally, customer behavior forecasting. We examine alternative strategies for integrating time-varying and non-variant customer features in one network architecture. In this scope, we also assess hybrid approaches that incorporate the outputs of DNNs in conventional CCP models. Using a comprehensive panel data set from a large financial services company, we find recurrent neural networks to outperform transformer architectures when focusing on time-varying RFM features. This finding is confirmed when time-invariant customer features are included, independent of the specific form of feature integration. Finally, we find no statistical evidence that hybrid approaches (based on regularized logistic regression and extreme gradient boosting) improve predictive performance—highlighting that DNNs and especially recurrent neural networks are suitable standalone classifiers for CCP using time-varying RFM measures. [ABSTRACT FROM AUTHOR]

Background: Virtual reality (VR) offers significant potential for hands‐on learning environments by providing immersive and visually stimulating experiences. Interacting with such environments can bring numerous benefits to learning, including enhanced engagement, knowledge construction, and higher‐order thinking. However, many current VR studies in hands‐on learning tend to utilise one‐way learning materials, limiting participants' ability to interact with and reflect on their actions and learning experiences. Moreover, these studies often neglect to assess learners' capacity to transfer their skills from VR learning to real‐world scenarios. Therefore, this study aims to investigate participants' engagement, learning outcomes, higher‐order thinking, and their ability to apply acquired skills in real‐world contexts. Method and Objective: Participants were immersed in a hands‐on learning environment in VR, where they received feedback and engaged in reflection during the learning process. This study recruited 68 university students to participate in the experiment, employing a quasi‐experimental design. Participants experienced learning units both with and without reflection on the feedback. The theme of these learning units was related to embedded systems, encompassing topics such as the assembly of embedded components and Python programming. The investigation aimed to assess whether reflection in VR could enhance cognitive levels, engagement, real‐world hands‐on tasks abilities, and higher‐order thinking. Results: The research results indicate that in the VR hands‐on learning environment, participants engage in reflection through the provided feedback, effectively enhancing their engagement, cognitive levels, and hands‐on task abilities. Simultaneously, it also successfully assists participants in developing problem‐solving skills and critical thinking in higher‐order thinking. Conclusions: Participants actively engaged in reflection on their own learning tasks and actions within the hands‐on learning environment, enabling them to develop a deeper understanding of the learning material and enhance their real‐world hands‐on tasks abilities, we encourage the integration of reflection strategies in VR learning environments for hands‐on learning, as they can yield positive benefits for learners. Lay Description: What is already known about this topic: Virtual reality learning environments can enhance students' cognitive levels.Higher‐order thinking has a significant impact on hands‐on learning.Reflection has an important influence on the cognitive process. What this paper adds: Providing reflection through feedback in a virtual reality environment increases learning engagement and promotes higher‐order thinking.Reflection in virtual reality enhances cognitive levels and practical abilities. Implications for practice and/or policy: We demonstrated the effectiveness of providing reflection through feedback in a VR hands‐on learning environment.Learners, through reflection in VR, enhance higher‐order thinking, engagement, cognitive levels, and practical abilities. What are the 1 or 2 major takeaways from the study: Providing reflection in VR learning environments used for training or hands‐on learning can effectively promote cognitive levels, engagement, higher‐order thinking abilities, and practical skills.Through VR reflection, we reveal the potential of cultivating higher‐order thinking through VR. [ABSTRACT FROM AUTHOR]

This paper proposes normalizing flow‐based image super‐resolution techniques using attention modules. In the proposed method, the features of the low‐resolution images are extracted using a Swin Transformer. Furthermore, multi‐head attention in the flow layers makes effective use of the feature maps. This architecture enables the efficient injection of low‐resolution image features extracted by the transformer into the flow layer. Experimental results at x4 magnifications showed that the proposed method achieved state‐of‐the‐art performance for quantitative metrics and visual quality among single‐loss architectures. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

In view of the scarcity, high cost and lack of diversity of three-dimensional (3D) face datasets, this paper designs an end-to-end self-supervised learning 3D face reconstruction network, which uses single 2D face image as input. The model bypasses the 3D face datasets and only uses the 2D face datasets for training to achieve high-precision 3D face reconstruction without any 3D face prior. First, the improved ResNet50 feature extraction module is introduced to extract and characterize the input image by deep convolutional network. Then, a lightweight convolutional block attention module is added to the face prediction subnetwork. On the one hand, channel attention extracts different information included in the image, and on the other hand spatial attention finds the location of the information. So, the serialized attention operation could accurately find the features required for different parameter predictions, further improving face reconstruction parameters’ prediction accuracy. Finally, training, ablation and comparison experiments were conducted on CelebFaces Attributes, basel face model and Photoface datasets, and the combined loss function of pixel loss and perception loss was selected. The pixel loss function was calculated at the pixel microscopic level, and the perception loss function was calculated at the image macroscopic convolution level. The combination of the two could complement each other. Compared with the historical optimal results of the same network structure, the scale-invariant depth error and mean angle deviation of the proposed algorithm are improved by 5.2% and 8.2%, respectively. Experimental results strongly prove the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

This paper presents a classification model for eye diseases utilizing attention mechanisms to learn features from fundus images and structures. The study focuses on diagnosing glaucoma by extracting retinal vessels and the optic disc from fundus images using a ResU-Net-based segmentation model and Hough Circle Transform, respectively. The extracted structures and preprocessed images were inputted into a CNN-based multi-input model for training. Comparative evaluations demonstrated that our model outperformed other research models in classifying glaucoma, even with a smaller dataset. Ablation studies confirmed that using attention mechanisms to learn fundus structures significantly enhanced performance. The study also highlighted the challenges in normal case classification due to potential feature degradation during structure extraction. Future research will focus on incorporating additional fundus structures such as the macula, refining extraction algorithms, and expanding the types of classified eye diseases. [ABSTRACT FROM AUTHOR]

In the process of hikers' choosing a destination, searching for information is one of the important elements, playing a decisive role in decision-making. Based on the Baidu Index for "hiking," this paper analyzes the spatial and temporal characteristics of and factors that influenced network attention to hiking in China from 2016 to 2021. The study found that (1) Network attention to hiking in China was generally relatively stable across the period studied, with highly uneven distribution between different months. The search volume was higher on weekends, and mobile searches increased year by year, far exceeding computer searches. (2) Different regions in China experienced different levels of network attention, with the highest levels in the east, followed by the center, and the lowest in the west. Except for East China, network attention to hiking was highly unevenly distributed within each region. (3) The COVID-19 pandemic increased the geographical concentration index and coefficient of variation but reduced the primacy index. A region's level of economic development, degree of network development, population size, and population age structure are proposed as factors that affect network attention to hiking. [ABSTRACT FROM AUTHOR]

Involuntary autobiographical memories (IAMs) have been typically studied with paper diaries, kept for a week or longer. However, such studies are unable to capture the true frequency of IAMs, nor the level of detail that would give new insights into the mechanisms of IAMs. To address this gap, a new audio-recording method was developed and tested on the first author who recorded 674 IAMs while driving a car on a 30–40-minute-long habitual route on 20 occasions. Results revealed very high frequency of IAMs (almost 34 per journey) that were reported more often in response to dynamic (one-off) than static cues. Moreover, a substantial number of memory chains and long-term priming of IAMs by previously encountered incidental stimuli were also recorded. Based on these results, a new theoretical model is proposed in which the occurrence of IAMs is determined by an interplay of factors at the time of the IAM, such as the type of ongoing activity and internal or external triggers, as well as different types of long-term priming. The results also have practical implications for studying mind-wandering and safety issues in driving and aircraft-flying, where periods of concentration are followed by monotony and less demanding tasks. [ABSTRACT FROM AUTHOR]

Unsupervised action recognition based on spatiotemporal fusion feature extraction has attracted much attention in recent years. However, existing methods still have several limitations: (1) The long-term dependence relationship is not effectively extracted at the time level. (2) The high-order motion relationship between non-adjacent nodes is not effectively captured at the spatial level. (3) The model complexity is too high when the cascade layer input sequence is long, or there are many key points. To solve these problems, a Multiple Distilling-based spatial-temporal attention (MD-STA) networks is proposed in this paper. This model can extract temporal and spatial features respectively and fuse them. Specifically, we first propose a Screening Self-attention (SSA) module; this module can find long-term dependencies in distant frames and high-order motion patterns between non-adjacent nodes in a single frame through a sparse metric on dot product pairs. Then, we propose the Frames and Keypoint-Distilling (FKD) module, which uses extraction operations to halve the input of the cascade layer to eliminate invalid key points and time frame features, thus reducing time and memory complexity. Finally, the Dim-reduction Fusion (DRF) module is proposed to reduce the dimension of existing features to further eliminate redundancy. Numerous experiments were conducted on three distinct datasets: NTU-60, NTU-120, and UWA3D, showing that MD-STA achieves state-of-the-art standards in skeleton-based unsupervised action recognition. [ABSTRACT FROM AUTHOR]

Joint entity-relation extraction is a fundamental task in the construction of large-scale knowledge graphs. This task relies not only on the semantics of the text span but also on its intricate connections, including classification and structural details that most previous models overlook. In this paper, we propose the incorporation of this information into the learning process. Specifically, we design a novel two-dimensional word-pair tagging method to define the task of entity and relation extraction. This allows type markers to focus on text tokens, gathering information for their corresponding spans. Additionally, we introduce a multi-level attention neural network to enhance its capacity to perceive structure-aware features. Our experiments show that our approach can overcome the limitations of earlier tagging methods and yield more accurate results. We evaluate our model using three different datasets: SciERC, ADE, and CoNLL04. Our model demonstrates competitive performance compared to the state-of-the-art, surpassing other approaches across the majority of evaluated metrics. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have shown remarkable performance across a wide range of fields, including image recognition, natural language processing, and speech processing. However, recent studies indicate that DNNs are highly vulnerable to well-crafted adversarial samples, which can cause incorrect classifications and predictions. These samples are so similar to the original ones that they are nearly undetectable by human vision, posing a significant security risk to DNNs in the real world due to the impact of adversarial attacks. Currently, the most common adversarial attack methods explicitly add adversarial perturbations to image samples, often resulting in adversarial samples that are easier to distinguish by humans. To address this issue, we are motivated to develop more effective methods for generating adversarial samples that remain undetectable to human vision. This paper proposes a pixel-level adversarial attack method based on attention mechanism and high-frequency information separation, named DIPA. Specifically, our approach involves constructing an attention suppression loss function and utilizing gradient information to identify and perturb sensitive pixels. By suppressing the model's attention to the correct classes, the neural network is misled to focus on irrelevant classes, leading to incorrect judgments. Unlike previous studies, DIPA enhances the attack of adversarial samples by separating the imperceptible details in image samples to more effectively hide the adversarial perturbation while ensuring a higher attack success rate. Our experimental results demonstrate that under the extreme single-pixel attack scenario, DIPA achieves higher attack success rates for neural network models with various architectures. Furthermore, the visualization results and quantitative metrics illustrate that the DIPA can generate more imperceptible adversarial perturbation. [ABSTRACT FROM AUTHOR]

Similar to convolutional neural networks for image processing, existing analysis methods for 3D point clouds often require the designation of a local neighborhood to describe the local features of the point cloud. This local neighborhood is typically manually specified, which makes it impossible for the network to dynamically adjust the receptive field's range. If the range is too large, it tends to overlook local details, and if it is too small, it cannot establish global dependencies. To address this issue, we introduce in this paper a new concept: receptive field space (RFS). With a minor computational cost, we extract features from multiple consecutive receptive field ranges to form this new receptive field space. On this basis, we further propose a receptive field space attention mechanism, enabling the network to adaptively select the most effective receptive field range from RFS, thus equipping the network with the ability to adjust granularity adaptively. Our approach achieved state-of-the-art performance in both point cloud classification, with an overall accuracy (OA) of 94.2%, and part segmentation, achieving an mIoU of 86.0%, demonstrating the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Previous research has shown that attentiveness (kikubari) is a significant aspect of politeness in Japanese. The aim of this paper is to expand on earlier research on attentiveness by using Twitter data and examine how Japanese lay people understand and/or evaluate attentiveness and how attentiveness manifests politeness. The data for this study were 600 Japanese tweets which contain attentiveness. They were coded based on analysis of the content and analysed both quantitatively and qualitatively. The results show that Japanese lay people evaluate attentiveness positively and that they think attentiveness is important in most cases. These results reflect a commonly held belief in Japanese culture, namely that attentiveness is a virtue. In some posts, the demonstrators of attentiveness appeared to infer the needs of the potential recipients and made pre-emptive offers, as they had known the situations of the potential recipients. Attentiveness in such posts coincides with the definition of attentiveness in previous research. In some other posts, attentiveness is used in the sense of consideration, which was included in the conceptualisation of politeness in Japanese. These results confirmed earlier findings and further our understanding of them through concrete examples from Twitter. [ABSTRACT FROM AUTHOR]

Philosophers of perception often claim that usual perceptual experiences not only present particulars but also phenomenally present them as particulars. Nevertheless, despite the initial plausibility of this thesis, it is not clear what exactly it means to say that particularity is phenomenally presented. The paper aims to provide a deeper analysis of the claim that perceptual experiences phenomenally present objects as particulars. In doing so, I distinguish two theses regarding phenomenally presented particularity: Generic Particularity and Specific Particularity. According to the first thesis, vision phenomenally presents particularity of objects, understood as a general characteristic that may be shared by many entities. The second thesis states that vision phenomenally presents particularity of objects, understood as an individual characteristic unique to each particular. I argue that, relying on knowledge concerning the functioning of perceptual mechanisms, vision does not phenomenally present generic particularity but it has certain abilities for presenting specific particularity. [ABSTRACT FROM AUTHOR]

Measurement based care (MBC), a practice that uses patient reported outcome measures (PROMs), is not widely used in behavioral health settings and little is known about the patient experience with MBC in safety-net settings. This study aimed to understand patient experiences completing PROMs on paper when presenting to an outpatient, behavioral health setting within a public safety-net hospital. Semi-structured interviews were conducted with 22 participants in English and Spanish. Participants were 42 years old (SD = 12.7), mostly white (36.4%) and Black (31.8%). Thematic analysis was used to analyze findings. Overall, participants were engaged with PROMs and described them as helpful for themselves and their clinicians. Participants also expressed themes focused on PROMs user-friendliness, including formatting, time to complete measures, and participant characteristics such as attention and literacy. These findings are important to consider to ensure equitable access to MBC when implemented in behavioral health in the health safety-net setting. [ABSTRACT FROM AUTHOR]

Few-shot learning for image classification comes up as a hot topic in computer vision, which aims at fast learning from a limited number of labeled images and generalize over the new tasks. In this paper, motivated by the idea of Fisher Score, we propose a Discriminative Local Descriptors Attention model that uses the ratio of intra-class and inter-class similarity to adaptively highlight the representative local descriptors without introducing any additional parameters, while most of the existing local descriptors based methods utilize the neural networks that inevitably involve the tedious parameter tuning. Experiments on four benchmark datasets show that our method achieves higher accuracy compared with the state-of-art approaches for few-shot learning. Specifically, our method is optimal on the CUB-200 dataset, and outperforms the second best competitive algorithm by 4.12 % and 0.49 % under the 5-way 1-shot and 5-way 5-shot settings, respectively. [ABSTRACT FROM AUTHOR]

The accurate and automated segmentation of neurons in electron microscopy (EM) images presents a challenging problem in neuroscience. In this paper, we propose a deep learning (DL)-based neuron segmentation approach using a relatively shallow residual deconvolutional neural network (DNN) as the core. Our proposed segmentation framework differs from most EM image segmentation networks that use original images as input, as we suggest using modified morphological features with attention characteristics as input instead. We calculate Bhattacharyya distances in morphology feature space to provide attention features, which are then concatenated with the original image and used as input to the segmentation network. By attending to membrane pixels, our network efficiently highlights the discrimination between membrane boundaries and background pixels. To remove noise pixels in the segmentation map while preserving membrane boundaries in the final result, the dilated version of the output is then processed using a guided filtering scenario. Our proposed model outperforms several competing DL methods such as DeepLabv3 as well as different versions of deconvolutional neural networks on the ISBI 2012 dataset in terms of various image segmentation metrics. The proposed attention-based morphological guided framework can help advance research in neuroscience by providing an automated and accurate segmentation of neurons in EM images. [ABSTRACT FROM AUTHOR]

This paper presents rational inattention as a new, transdiagnostic theory of information seeking in neurodevelopmental conditions that have uneven cognitive and socio‐emotional profiles, including developmental language disorder (DLD), dyslexia, dyscalculia and autism. Rational inattention holds that the optimal solution to minimizing epistemic uncertainty is to avoid imprecise information sources. The key theoretical contribution of this report is to endogenize imprecision, making it a function of the primary neurocognitive difficulties that have been invoked to explain neurodivergent phenotypes, including deficits in auditory perception, working memory, procedural learning and the social brain network. We argue that disengagement with information sources with low endogenous precision (e.g. speech in DLD, orthography‐phonology mappings in dyslexia, numeric stimuli in dyscalculia and social signals in autism) constitutes resource‐rational behaviour. We demonstrate the strength of this account in a series of computational simulations. In experiment 1, we simulate information seeking in artificial agents mimicking an array of neurodivergent phenotypes, which optimally explore a complex learning environment containing speech, text, numeric stimuli and social cues. In experiment 2, we simulate optimal information seeking in a cross‐modal dual‐task paradigm and qualitatively replicate empirical data from children with and without DLD. Across experiments, simulated agents' only aim was to maximally reduce epistemic uncertainty, with no difference in reward across information sources. We show that rational inattention emerges naturally in specific neurodivergent phenotypes as a function of low endogenous precision. For instance, an agent mimicking the DLD phenotype disengages with speech (and preferentially engages with alternative precise information sources) because endogenous imprecision renders speech not conducive to information gain. Because engagement is necessary for learning, simulation demonstrates how optimal information seeking may paradoxically contribute negatively to an already delayed learning trajectory in neurodivergent children. Research Highlights: We present the first comprehensive theory of information seeking in neurodivergent children to date, centred on the notion of rational inattention.We demonstrate the strength of this account in a series of computational simulations involving artificial agents mimicking specific neurodivergent phenotypes that optimally explore a complex learning environment containing speech, text, numeric stimuli, and social cues.We show how optimal information seeking may, paradoxically, contribute negatively to an already delayed learning trajectory in neurodivergent children.This report advances our understanding of the factors shaping short‐term decision making and long‐term learning in neurodivergent children. [ABSTRACT FROM AUTHOR]

Brain–Computer Interface is tested as a successful method in improving human cognitive functions such as attention and memory. Attention plays a significant role in areas ranging from a person's day-to-day life to educational domain and professional activities. When attention is evaluated using camera-based techniques, the users may suffer privacy issues. Using Brain–Computer Interface (BCI) to obtain a measure of attention will be useful in this regard. The paper proposes a Human Attention Recognition System (HARS) in which EEG signal acquisition is used to obtain the attention of the individual, Renyi's entropy-based mutual information method is used for feature selection and a deep learning-based classifier is used to classify the signals. HADS is not camera-based: therefore, faces of the subjects are not revealed. EEG signals were collected using the Ultracortex Mark III dry electrodes and were visualised using OpenBCI GUI (Graphical User Interface). The experiment is validated using the publicly available Confused Student EEG dataset from Kaggle, giving an accuracy of 99.21%. The results indicate that the proposed method can identify attention levels accurately and can be effectively used in educational systems, biofeedback and medical research. [ABSTRACT FROM AUTHOR]

Background: There is inconclusive evidence for the effects of various leisure activities on attention performance in children. The literature reports inconsistent associations between activities such as physical activities or media use. To date, no study has thoroughly examined the various factors influencing attentional performance in a larger cohort of healthy children. This study aims to close this research gap. Methods: From 2018 to 2019, the Leipzig School Nutrition Study collected data from 1215 children and their families. The children report their dietary behavior (using CoCu- Questionnaire), especially their participation in school lunch and their breakfast habits, through a paper questionnaire. Furthermore, attention performance was assessed using a validated test (FAIR-2) at school. Data on physical activity, media consumption, family eating habits and socio-economic status (SES) were collected from parents using questionnaires. Associations between attention and influencing factors were estimated using hierarchical linear regression. Analyses were adjusted for age, SES, and school type. Results: Attending upper secondary schools (ßadj= 23.6, p < 0.001) and having a higher SES (ß= 1.28, p < 0.001) was associated with higher attention performance. Children doing leisure-time sports (ßadj= 4.18, p = 0.046) or reading books for at least one hour/weekday showed better attention performance (ßadj= 3.8, p = 0.040). Attention performance was also better in children having no electronic devices in the bedroom (ßadj= 13.0, p = 0.005) and in children whose parents limited their children's Internet access (ßadj= 5.2, p = 0.012). We did not find any association between nutritional habits and attention performance. Conclusions: We found that fostering modifiable habits such as reading and physical activity could enhance attention performance. These findings have substantial implications for the development of prevention and intervention programs that aim to improve attention in schoolchildren. It is important to note, however, that social status as a hardly modifiable factor also impacts attention performance. Therefore, interventions should address personal habits in a systemic approach considering the child's social status. Trial registration: The study is retrospectively registered with the German Clinical Trials Register (DRKS00017317, registration: 05-29-2019). [ABSTRACT FROM AUTHOR]

The remarkable human ability to predict others' intent during physical interactions develops at a very early age and is crucial for development. Intent prediction, defined as the simultaneous recognition and generation of human–human interactions, has many applications such as in assistive robotics, human–robot interaction, video and robotic surveillance, and autonomous driving. However, models for solving the problem are scarce. This paper proposes two attention-based agent models to predict the intent of interacting 3D skeletons by sampling them via a sequence of glimpses. The novelty of these agent models is that they are inherently multimodal, consisting of perceptual and proprioceptive pathways. The action (attention) is driven by the agent's generation error, and not by reinforcement. At each sampling instant, the agent completes the partially observed skeletal motion and infers the interaction class. It learns where and what to sample by minimizing the generation and classification errors. Extensive evaluation of our models is carried out on benchmark datasets and in comparison to a state-of-the-art model for intent prediction, which reveals that classification and generation accuracies of one of the proposed models are comparable to those of the state of the art even though our model contains fewer trainable parameters. The insights gained from our model designs can inform the development of efficient agents, the future of artificial intelligence (AI). [ABSTRACT FROM AUTHOR]

Micro-expressions (MEs) play such an important role in predicting a person's genuine emotions, as to make micro-expression recognition such an important resea rch focus in recent years. Most recent researchers have made efforts to recognize MEs with spatial and temporal information of video clips. However, because of their short duration and subtle intensity, capturing spatio-temporal features of micro-expressions remains challenging. To effectively promote the recognition performance, this paper presents a novel paralleled dual-branch attention-based spatio-temporal fusion network (PASTFNet). We jointly extract short- and long-range spatial relationships in spatial branch. Inspired by the composite architecture of the convolutional neural network (CNN) and long short-term memory (LSTM) for temporal modeling, we propose a novel attention-based multi-scale feature fusion network (AMFNet) to encode features of sequential frames, which can learn more expressive facial-detailed features for it implements the integrated use of attention and multi-scale feature fusion, then design an aggregation block to aggregate and acquire temporal features. At last, the features learned by the above two branches are fused to accomplish expression recognition with outstanding effect. Experiments on two MER datasets (CASMEII and SAMM) show that the PASTFNet model achieves promising ME recognition performance compared with other methods. [ABSTRACT FROM AUTHOR]