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]

Background: Drug combination treatments have proven to be a realistic technique for treating challenging diseases such as cancer by enhancing efficacy and mitigating side effects. To achieve the therapeutic goals of these combinations, it is essential to employ multi-targeted drug combinations, which maximize effectiveness and synergistic effects. Results: This paper proposes 'MultiComb', a multi-task deep learning (MTDL) model designed to simultaneously predict the synergy and sensitivity of drug combinations. The model utilizes a graph convolution network to represent the Simplified Molecular-Input Line-Entry (SMILES) of two drugs, generating their respective features. Also, three fully connected subnetworks extract features of the cancer cell line. These drug and cell line features are then concatenated and processed through an attention mechanism, which outputs two optimized feature representations for the target tasks. The cross-stitch model learns the relationship between these tasks. At last, each learned task feature is fed into fully connected subnetworks to predict the synergy and sensitivity scores. The proposed model is validated using the O'Neil benchmark dataset, which includes 38 unique drugs combined to form 17,901 drug combination pairs and tested across 37 unique cancer cells. The model's performance is tested using some metrics like mean square error ( MSE ), mean absolute error ( MAE ), coefficient of determination ( R 2 ), Spearman, and Pearson scores. The mean synergy scores of the proposed model are 232.37, 9.59, 0.57, 0.76, and 0.73 for the previous metrics, respectively. Also, the values for mean sensitivity scores are 15.59, 2.74, 0.90, 0.95, and 0.95, respectively. Conclusion: This paper proposes an MTDL model to predict synergy and sensitivity scores for drug combinations targeting specific cancer cell lines. The MTDL model demonstrates superior performance compared to existing approaches, providing better results. [ABSTRACT FROM AUTHOR]

This paper proposes a novel multi-view ensemble predictor model that is designed to address the challenge of determining synergistic drug combinations by predicting both the synergy score value values and synergy class label of drug combinations with cancer cell lines. The proposed methodology involves representing drug features through four distinct views: Simplified Molecular-Input Line-Entry System (SMILES) features, molecular graph features, fingerprint features, and drug-target features. On the other hand, cell line features are captured through four views: gene expression features, copy number features, mutation features, and proteomics features. To prevent overfitting of the model, two techniques are employed. First, each view feature of a drug is paired with each corresponding cell line view and input into a multi-task attention deep learning model. This multi-task model is trained to simultaneously predict both the synergy score value and synergy class label. This process results in sixteen input view features being fed into the multi-task model, producing sixteen prediction values. Subsequently, these prediction values are utilized as inputs for an ensemble model, which outputs the final prediction value. The 'MVME' model is assessed using the O'Neil dataset, which includes 38 distinct drugs combined across 39 distinct cancer cell lines to output 22,737 drug combination pairs. For the synergy score value, the proposed model scores a mean square error (MSE) of 206.57, a root mean square error (RMSE) of 14.30, and a Pearson score of 0.76. For the synergy class label, the model scores 0.90 for accuracy, 0.96 for precision, 0.57 for kappa, 0.96 for the area under the ROC curve (ROC-AUC), and 0.88 for the area under the precision-recall curve (PR-AUC). Scientific contribution: This paper presents an enhanced synergistic drug combination model by utilizing four different feature views for drugs and four views for cancer cell lines. Each view is then input into a multi-task deep learning model to predict both the synergy score and class label simultaneously. To address the challenge of managing diverse views and their corresponding prediction values while avoiding overfitting, an ensemble model is applied. [ABSTRACT FROM AUTHOR]

Medical image segmentation through the use of deep learning is becoming a trend targeting to automate disease detection and provide effective treatment. Traditionally huge manual efforts are associated with medical image processing by medical staff. The wide use of neural networks driven by the progressive advancement in computing power and the availability of training data provides instrumental means to automate medical image processing. A polyp refers to an abnormal growth that can occur in various parts of the body. While the majority of polyps are noncancerous or benign, there are instances where certain types can develop into cancer. Detecting and segmenting polyps is highly valuable for identifying early signs and potentially enabling more effective treatment of colon cancer. In this paper, we introduce a novel method for segmenting polyp images. The proposed method utilizes convolutional neural networks (CNNs) and employs an enhanced attention mechanism. To cater to a more granular attention view, this paper enhances the Convolutional Block Attention Module by introducing the multi‐focal channel attention (MFCA) concept, which we call MFCA. In the proposed MFCA channel attention, focal attention spots allow us to consider scattered areas of interest more effectively. To evaluate the effectiveness of the proposed method, multiple experiments are conducted on five well‐known benchmark datasets for polyp image segmentation: Kvasir, CVC‐Clinic DB, CVC‐Colon DB, CVC‐T, and ETIS‐Larib. Various testing scenarios are examined, including the impact of two focal attention spots and four focal attention spots. The experimental results demonstrated that the proposed method achieved superior performance compared to previous state‐of‐the‐art techniques on two of the benchmark datasets, and ranked second on a third dataset. [ABSTRACT FROM AUTHOR]

Traditional methods for object detection typically necessitate a substantial amount of training data, and creating high-quality training data is time-consuming. We propose a novel Few-Shot Object Detection network (FSODv2) in this paper that aims to detect objects from previously unseen categories using only a few annotated examples. Attention RPN, Multi-Relation Detector, and Contrastive Training strategy are central to our method (Fan et al., in: CVPR, 2020), which exploit similarity between few shot support set and query set to detect novel objects while suppressing false detection in the background. We also contribute a new dataset, FSOD-1k, which contains 1000 categories of various objects with high-quality annotations to train our network. To the best of our knowledge, this is one of the first datasets designed for few-shot object detection. This paper improves our FSOD model through well-designed model calibration in three areas: (1) we propose an improved FPN with multi-scale support inputs to calibrate the multi-scale support-query feature matching by exploiting multi-scale features from the same support image with different input scales; (2) we introduce a support classification supervision branch to calibrate the support feature supervision, aligning to the query feature training supervision; (3) we propose backbone calibration to preserve prior knowledge while alleviating backbone bias toward base classes by employing classification dataset to help our model calibration procedure, where such dataset has previously only been used for pre-training in other related works. Besides, we propose a Fast Attention RPN to improve evaluation speed and save computational memory during inference. Once trained, our few-shot network can detect objects from previously unseen categories without further training or fine-tuning, resulting in new state-of-the-art performance on different datasets in the few-shot setting. Our method is general in scope and has numerous potential applications. The dataset link is https://github.com/fanq15/Few-Shot-Object-Detection-Dataset. [ABSTRACT FROM AUTHOR]

Featured Application: This study focuses on the segmentation of 3D medical images. Due to the difficulty in obtaining labels for medical images, it is challenging to achieve effective segmentation using fully supervised networks. Therefore, semi-supervised networks have become a better choice. To enhance the segmentation performance of semi-supervised learning methods on the left-atrium database, this paper proposes a triple consistency segmentation network based on squeeze–excitation (SETC-Net). Our semi-supervised medical image segmentation network achieves state-of-the-art segmentation performance on the left-atrium database. Convolutional neural networks (CNNs) have achieved remarkable success in fully supervised medical image segmentation tasks. However, the acquisition of large quantities of homogeneous labeled data is challenging, making semi-supervised training methods that rely on a small amount of labeled data and pseudo-labels increasingly popular in recent years. Most existing semi-supervised learning methods, however, underestimate the importance of the unlabeled regions during training. This paper posits that these regions may contain crucial information for minimizing the model's uncertainty prediction. To enhance the segmentation performance of the left-atrium database, this paper proposes a triple consistency segmentation network based on the squeeze-and-excitation mechanism (SETC-Net). Specifically, the paper constructs a symmetric architectural unit called SEConv, which adaptively recalibrates the feature responses in the channel direction by modeling the inter-channel correlations. This allows the network to adaptively weigh each channel according to the task's needs, thereby emphasizing or suppressing different feature channels. Moreover, SETC-Net is composed of an encoder and three slightly different decoders, which convert the prediction discrepancies among the three decoders into unsupervised loss through a constructed iterative pseudo-labeling scheme, thus encouraging consistent and low-entropy predictions. This allows the model to gradually capture generalized features from these challenging unmarked regions. We evaluated the proposed SETC-Net on the public left-atrium (LA) database. The proposed method achieved an excellent Dice score of 91.14% using only 20% of the labeled data. The experiments demonstrate that the proposed SETC-Net outperforms seven current semi-supervised methods in left-atrium segmentation and is one of the best semi-supervised segmentation methods on the LA database. [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]

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]

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]

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]

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]

• 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]

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]

Animating gaze behavior is crucial for creating believable virtual characters, providing insights into their perception and interaction with the environment. In this paper, we present an efficient yet natural‐looking gaze animation model applicable to real‐time walking characters exploring natural environments. We address the challenge of dynamic gaze adaptation by combining findings from neuroscience with a data‐driven saliency model. Specifically, our model determines gaze focus by considering the character's locomotion, environment stimuli, and terrain conditions. Our model is compatible with both automatic navigation through pre‐defined character trajectories and user‐guided interactive locomotion, and can be configured according to the desired degree of visual exploration of the environment. Our perceptual evaluation shows that our solution significantly improves the state‐of‐the‐art saliency‐based gaze animation with respect to the character's apparent awareness of the environment, the naturalness of the motion, and the elements to which it pays attention. [ABSTRACT FROM AUTHOR]

The surge in the intelligent information age has led to a growing need for enhanced computing power in smart mobile devices. However, the accompanying increase in computing power brings about a significant challenge — high power consumption. This poses a notable hurdle for mobile devices that prioritize sustainability performance. Effectively addressing power consumption estimation is crucial for overcoming this sustainability issue. In this paper, we propose using a branching parallel neural networks (BPNS) that consists of FCNN-LSTM and a attention mechanism to estimate the power consumption of a device. In addition, a data stabilization module is incorporated into the framework to improve the power estimation accuracy. We implement and assess the performance of BPNS for online estimation across diverse smart mobile devices, conducting a comparative analysis with commonly used neural networks. Notably, our approach achieves a deviation of 0.28W, 0.65W and 0.76W for online estimation on three smart mobile devices, and outperforms other methods in terms of estimation accuracy and computational cost. [ABSTRACT FROM AUTHOR]

As a key factor to determine the form of future war, human-machine fusion has attracted the attention of experts in the military field of various countries from its inception to its rise, and it is a necessary means to promote the cooperation between human intelligence and machine intelligence. In this paper, the current research status, relevant important concepts and practical applications of human-machine fusion systems are introduced. Then, the development from unmanned systems to human-machine fusion is analyzed. Moreover, the relevant theories and cooperation strategies of human-computer fusion are summarized. The implementation framework, collaborative mechanism, and development analysis are obtained. The performance optimization methods and key technologies of collaborative optimization are deeply analyzed. [ABSTRACT FROM AUTHOR]

Gender stereotypes may impact voters' candidate choices. But do gender stereotypes impact voters' attention when learning about candidates? This paper explores whether citizens take part in gender biased information acquisition when learning about women and men candidates. In an experiment, I use eye tracking to measure respondents' attention to gender stereotype‐consistent and inconsistent information. The results indicate that citizens do not differ in their attention to different candidate information according to candidate gender. Additionally, respondents' own sex does not make a difference in their attention to masculine‐ and feminine‐stereotyped information for women or men candidates. These findings provide an important specification of the mechanism behind gender bias in candidate choices: the bias appears to be different standards of judgment for candidates of different genders, not different compositions of information being judged for candidates of different genders. [ABSTRACT FROM AUTHOR]

Image restoration in adverse weather conditions is a difficult task in computer vision. In this paper, we propose a novel transformer-based framework called GridFormer which serves as a backbone for image restoration under adverse weather conditions. GridFormer is designed in a grid structure using a residual dense transformer block, and it introduces two core designs. First, it uses an enhanced attention mechanism in the transformer layer. The mechanism includes stages of the sampler and compact self-attention to improve efficiency, and a local enhancement stage to strengthen local information. Second, we introduce a residual dense transformer block (RDTB) as the final GridFormer layer. This design further improves the network's ability to learn effective features from both preceding and current local features. The GridFormer framework achieves state-of-the-art results on five diverse image restoration tasks in adverse weather conditions, including image deraining, dehazing, deraining & dehazing, desnowing, and multi-weather restoration. The source code and pre-trained models will be released. [ABSTRACT FROM AUTHOR]

Traditional validation processes for psychological surveys tend to focus on analyzing item responses instead of the cognitive processes that participants use to generate these responses. When screening for invalid responses, researchers typically focus on participants who manipulate their answers for personal gain or respond carelessly. In this paper, we introduce a new invalid response process, discordant responding, that arises when participants disagree with the use of the survey and discuss similarities and differences between this response style and protective responding. Results show that nearly all participants reflect on the intended uses of an assessment when responding to items and may decline to respond or modify their responses if they are not comfortable with the way the results will be used. Incidentally, we also find that participants may misread survey instructions if they are not interactive. We introduce a short screener to detect invalid responses, the discordant response identifiers (DRI), which provides researchers with a simple validity tool to use when validating surveys. Finally, we provide recommendations about how researchers may use these findings to design surveys that reduce this response manipulation in the first place. [ABSTRACT FROM AUTHOR]

Robots in tomato greenhouses need to perceive the plant and plant parts accurately to automate monitoring, harvesting, and de-leafing tasks. Existing perception systems struggle with the high levels of occlusion in plants and often result in poor perception accuracy. One reason for this is because they use fixed cameras or predefined camera movements. Next-best-view (NBV) planning presents an alternate approach, in which the camera viewpoints are reasoned and strategically planned such that the perception accuracy is improved. However, existing NBV-planning algorithms are agnostic to the task-at-hand and give equal importance to all the plant parts. This strategy is inefficient for greenhouse tasks that require targeted perception of specific plant parts, such as the perception of leaf nodes for de-leafing. To improve targeted perception in complex greenhouse environments, NBV planning algorithms need an attention mechanism to focus on the task-relevant plant parts. In this paper, the role of attention in improving targeted perception using an attention-driven NBV planning strategy was investigated. Through simulation experiments using plants with high levels of occlusion and structural complexity, it was shown that focusing attention on task-relevant plant parts can significantly improve the speed and accuracy of 3D reconstruction. Further, with real-world experiments, it was shown that these benefits extend to complex greenhouse conditions with natural variation and occlusion, natural illumination, sensor noise, and uncertainty in camera poses. The results clearly indicate that using attention-driven NBV planning in greenhouses can significantly improve the efficiency of perception and enhance the performance of robotic systems in greenhouse crop production. • Method to plan the next-best viewpoint to reconstruct the nodes of tomato plants. • Adding attention mechanism improves the efficiency of next-best-view planning. • Performed systematic evaluations with both simulation and real-world tomato plants. • Effectively handles occlusion in complex greenhouse environments. [ABSTRACT FROM AUTHOR]

Brain tumors pose a serious threat to public health, impacting thousands of individuals directly or indirectly worldwide. Timely and accurate detection of these tumors is crucial for effective treatment and enhancing the quality of patients’ lives. The widely used brain imaging technique is magnetic resonance imaging, the precise identification of brain tumors in MRI images is challenging due to the diverse anatomical structures. This paper introduces an innovative approach known as the ensemble attention mechanism to address this challenge. Initially, the approach uses two networks to extract intermediate- and final-level feature maps from MobileNetV3 and EfficientNetB7. This assists in gathering the relevant feature maps from the different models at different levels. Then, the technique incorporates a co-attention mechanism into the intermediate and final feature map levels on both networks and ensembles them. This directs attention to certain regions to extract global-level features at different levels. Ensemble of attentive feature maps enabling the precise detection of various feature patterns within brain tumor images at both model, local, and global levels. This leads to an improvement in the classification process. The proposed system was evaluated on the Figshare dataset and achieved an accuracy of 98.94%, and 98.48% for the BraTS 2019 dataset which is superior to other methods. Thus, it is robust and suitable for brain tumor detection in healthcare systems. [ABSTRACT FROM AUTHOR]

To enhance the effectiveness of the Advanced Persistent Threat (APT) detection process, this research proposes a new approach to build and analyze the behavior profiles of APT attacks in network traffic. To achieve this goal, this study carries out two main objectives, including (i) building the behavior profile of APT IP in network traffic using a new intelligent computation method; (ii) analyzing and evaluating the behavior profile of APT IP based on a deep graph network. Specifically, to build the behavior profile of APT IP, this article describes using a combination of two different data mining methods: Bidirectional Long Short-Term Memory (Bi) and Attention (A). Based on the obtained behavior profile, the Dynamic Graph Convolutional Neural Network (DGCNN) is proposed to extract the characteristics of APT IP and classify them. With the flexible combination of different components in the model, the important information and behavior of APT attacks are demonstrated, not only enhancing the accuracy of detecting attack campaigns but also reducing false predictions. The experimental results in the paper show that the method proposed in this study has brought better results than other approaches on all measurements. In particular, the accuracy of APT attack prediction results (Precision) reached from 84 to 91%, higher than other studies of over 7%. These experimental results have proven that the proposed BiADG model for detecting APT attacks in this study is proper and reasonable. In addition, those experimental results have not only proven the effectiveness and superiority of the proposed method in detecting APT attacks but have also opened up a new approach for other cyber-attack detections such as distributed denial of service, botnets, malware, phishing, etc. [ABSTRACT FROM AUTHOR]

Technological change has produced a high-choice media environment in which selective exposure and news avoidance are increasingly feasible and common. The literature has suggested several correlates of news avoidance, and recent work has particularly emphasized the potential significance of negative affective responses to news. This paper argues for the use of psychophysiological methods to better understand how emotional responses drive news avoidance. In doing so, we question the assumption—evident both in the literature on physiology and news, and in the literature on news and newsmaking—that physiological activation is positively associated with attention. We also offer an expository analysis of data from a physiological experiment in which respondents viewed stories for which activation quite likely motivated increased prolonged attention amongst some respondents, but a desire to avoid that content amongst others. [ABSTRACT FROM AUTHOR]

Our reasons for emotions such as sadness, anger, resentment, and guilt often remain long after we cease experiencing these emotions. This is puzzling. If the reasons for these emotions persist, why do the emotions not persist? Does this constitute a failure to properly respond to our reasons? In this paper we provide a solution to this puzzle. Our solution turns on the close connection between the rationality of emotion and the rationality of attention, together with the differing reasons to which attention and emotion are properly responsive. [ABSTRACT FROM AUTHOR]

Attention is a fundamental cognitive mechanism whose primary function is to regulate and organize the flow of perceptions and actions shaping our mental life. Early cognitive models have highlighted aspects of sustained, selective, and executive control as essential components of attention. These three broad aspects can be further subdivided into subordinate operations, depending on whether the particular function is mostly driven by external stimulation (bottom-up attention) or relies on endogenous processes such as voluntary intentions or expectations (top-down attention). After several decades of cognitive neuroscience research, these different functions have been associated with specific circuits of brain regions. Based on the cognitive neuroscience framework, this paper presents a theory of attention development and discusses behavioral and brain evidence regarding the development of attention function during the first years of life. [ABSTRACT FROM AUTHOR]

Auditory steady-state response (ASSR) is the result of the brain's ability to follow and entrain its oscillatory activity to the phase and frequency of periodic auditory stimulation. Gamma-band ASSR has been increasingly investigated with intentions to apply it in neuropsychiatric disorders diagnosis as well as in brain–computer interface technologies. However, it is still debatable whether attention can influence ASSR, as the results of the attention effects of ASSR are equivocal. In our study, we aimed to systemically review all known articles related to the attentional modulation of gamma-band ASSRs. The initial literature search resulted in 1283 papers. After the removal of duplicates and ineligible articles, 49 original studies were included in the final analysis. Most analyzed studies demonstrated ASSR modulation with differing attention levels; however, studies providing mixed or non-significant results were also identified. The high versatility of methodological approaches including the utilized stimulus type and ASSR recording modality, as well as tasks employed to modulate attention, were detected and emphasized as the main causality of result inconsistencies across studies. Also, the impact of training, inter-individual variability, and time of focus was addressed. [ABSTRACT FROM AUTHOR]

Listening to music can span a continuum from passive consumption to active exploration, relying on processes of coping with the sounds as well as higher-level processes of sense-making. Revolving around the major questions of "what" and "how" to explore, this paper takes a naturalistic stance toward music listening, providing tools to objectively describe the underlying mechanisms of musical sense-making by weakening the distinction between music and non-music. Starting from a non-exclusionary conception of "coping" with the sounds, it stresses the exploratory approach of treating music as a sound environment to be discovered by an attentive listener. Exploratory listening, in this view, is an open-minded and active process, not dependent on simply recalling pre-existing knowledge or information that reduces cognitive processing efforts but having a high cognitive load due to the need for highly focused attention and perceptual readiness. Music, explored in this way, is valued for its complexity, surprisingness, novelty, incongruity, puzzlingness, and patterns, relying on processes of selection, differentiation, discrimination, and identification. [ABSTRACT FROM AUTHOR]

To address the issue of user preference drift and capture dynamic user preferences more accurately in sequence recommendation, this paper proposed a novel model named SILSSRec. The model initially leveraged categories and frequencies of items as side information to generate personalized user embeddings based on users' historical interaction sequences. Then it created personalized temporal interval embeddings by considering the time intervals between historical and current interactions, and integrated these embeddings with item feature embeddings to form personalized temporal embeddings. The model employed attention mechanisms and gated recurrent networks to extract users' long-term and short-term preferences from the embedding representations. Furthermore, it used contrastive learning to reinforce the feature representation of preferences, and an adaptive aggregation network dynamically combined these two types of preferences to form the final preference representation of users. Experiments on eight public datasets demonstrate that SILSSRec outperforms existing baseline models on evaluation metrics, with an average increase of 3.82% in AUC, 7.2% in recall rate, and 0.3% in precision. The results validate that SILSSRec performs well in various scenarios, effectively mitigating the preference drift issue and enhancing recommendation performance. [ABSTRACT FROM AUTHOR]

Currently, with the advancement of dual-clutch transmission (DCT) control systems and vehicle performance, it is necessary to develop better objective evaluation methods for DCT vehicles. The starting process is a critical element affecting the driving and riding experience of DCT vehicles. Therefore, it is crucial to establish and improve a starting process evaluation model for the objective evaluation to DCT vehicles and optimization to DCT control strategies. This paper proposes a new method to evaluate the DCT vehicle starting process objectively. The method analyzes and models the time-series signals of the driving data using the LSTM neural network and uses the attention mechanism to improve the evaluation performance and enhance the interpretability of the evaluation results. Taking the dynamic performance evaluation as an example, the evaluation results indicate that the proposed model is better than the conventional methods, showing notable efficacy and preponderance. [ABSTRACT FROM AUTHOR]

Segmenting sclera images for effective recognition under non-cooperative conditions poses a significant challenge due to the prevalent noise. While U-Net-based methods have shown success, their limitations in accurately segmenting objects with varying shapes necessitate innovative approaches. This paper introduces the spatiotemporal residual encoding and decoding network (SRU-Net), featuring multi-spatiotemporal feature integration (Ms-FI) modules and attention-pool mechanisms to enhance segmentation accuracy and robustness. Ms-FI modules within SRU-Net’s encoders and decoders identify salient feature regions and prune responses, while attention-pool modules improve segmentation robustness. To assess the proposed SRU-Net, we conducted experiments using six datasets, employing precision, recall, and F1-score metrics. The experimental results demonstrate the superiority of SRU-Net over state-of-the-art methods. Specifically, SRU-Net achieves F1-score values of 94.58%, 98.31%, 98.49%, 97.52%, 95.3%, 97.47%, and 93.11% for MSD, MASD, SVBPI, MASD+MSD, UBIRIS.v1, UBIRIS.v2, and MICHE, respectively. Further evaluation in recognition tasks, with metrics such as AUC, EER, VER@0.1%FAR, and VER@1%FAR considered for the six datasets. The proposed pipeline, comprising SRU-Net and auto encoders (AE), outperforms previous research for all datasets. Particularly noteworthy is the comparison of EER, where SRU-Net + AE exhibits the best recognition results, achieving an EER of 9.42%, 3.81%, and 5.73% for MSD, MASD, and MICHE datasets, respectively. [ABSTRACT FROM AUTHOR]

This paper illuminates how teachers are influenced by age, gender and sexuality in teaching about sex and relationships. In this analysis grounded in feminist theory, age, gender and sexuality are considered to be enacted as doings. Six interviews with teachers working with sexuality education in K-12 schools in Sweden were chosen from of a larger body of material consisting of 21 interviews with professionals engaged in school-based sexuality education. The six interviewees were selected because they explicitly addressed how teachers' age, gender and/or sexuality come to matter in the classroom. Findings show how male and female teachers organise their teaching in relation to normative expectations of age, gender and sexuality. In sexuality education, the diverse life-courses of (hetero)sexual women offer a wide range of pedagogic possibilities for female teachers to address issues of sexuality, consent and relationships whereas male teachers are constrained to doing safe(r) forms of masculinity by directing attention away from their bodies and experiences. In understanding these results, I argue that the figure of the tant has been key in forming the pedagogic backdrop to Swedish sexuality education, hence embedding a normative 'who' in the 'how' to teach sexuality education. [ABSTRACT FROM AUTHOR]

Convolutional neural networks trained with satellite image time series have demonstrated their potential in land cover classification in recent years. Nevertheless, the rationale leading to their decisions remains obscure by nature. Methods for providing relevant and simplified explanations of their decisions as well as methods for understanding their inner functioning have thus emerged. However, both kinds of methods generally work separately and no explicit connection between their findings is made available. This paper presents an innovative method for refining the explanations provided by channel-based attention mechanisms. It consists in identifying correspondence rules between neuronal activation levels and the presence of spatiotemporal patterns in the input data for each channel and target class. These rules provide both class-level and instance-level explanations, as well as an explicit understanding of the network operations. They are extracted using a state-of-the-art redescription mining algorithm. Experiments on the Reunion Island Sentinel-2 dataset show that both correct and incorrect decisions can be explained using convenient spatiotemporal visualizations. [ABSTRACT FROM AUTHOR]

Attentional engagement is known to vary on a moment-to-moment basis. However, few self-report methods can effectively capture dynamic fluctuations in attentional engagement over time. In the current paper, we evaluated the utility of stimulated recall, a method wherein individuals are asked to remember their subjective states while using a mnemonic cue, for the measurement of temporal changes in attentional engagement. Participants were asked to watch a video lecture, during which we assessed their in-the-moment levels of attentional engagement using intermittent thought probes. Then, we used stimulated recall by cueing participants with short video clips from the lecture to retrospectively assess the levels of attentional engagement they had experienced when they first watched those clips within the lecture. Experiment 1 assessed the statistical overlap between in-the-moment and video-stimulated ratings. Experiment 2 assessed the generalizability of video-stimulated recall across different types of lectures. Experiment 3 assessed the impact of presenting video-stimulated probe clips in non-chronological order. Experiment 4 assessed the effect of video-stimulated recall on its own. Across all experiments, we found statistically robust correspondence between in-the-moment and video-stimulated ratings of attentional engagement, illustrating a strong convergence between these two methods of assessment. Taken together, our findings indicate that stimulated recall provides a new and practical methodological approach that can accurately capture dynamic fluctuations in subjective attentional states over time. [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]

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]

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]

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]

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]

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]

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]

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]

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]

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]

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]

With the rapid development of information technology in modern society, the application of multimedia integration platform is more and more extensive. Speech recognition has become an important subject in the process of multimedia visual interaction. The accuracy of speech recognition is dependent on a number of elements, two of which are the acoustic characteristics of speech and the speech recognition model. Speech data is complex and changeable. Most methods only extract a single type of feature of the signal to represent the speech signal. This single feature cannot express the hidden information. And, the excellent speech recognition model can also better learn the characteristic speech information to improve performance. This work proposes a new method for speech recognition in multimedia visual interaction. First of all, this work considers the problem that a single feature cannot fully represent complex speech information. This paper proposes three kinds of feature fusion structures to extract speech information from different angles. This extracts three different fusion features based on the low-level features and higher-level sparse representation. Secondly, this work relies on the strong learning ability of neural network and the weight distribution mechanism of attention model. In this paper, the fusion feature is combined with the bidirectional long and short memory network with attention. The extracted fusion features contain more speech information with strong discrimination. When the weight increases, it can further improve the influence of features on the predicted value and improve the performance. Finally, this paper has carried out systematic experiments on the proposed method, and the results verify the feasibility. [ABSTRACT FROM AUTHOR]

The next Point-of-Interest (POI) recommendation, in recent years, has attracted an extensive amount of attention from the academic community. RNN-based methods cannot establish effective long-term dependencies among the input sequences when capturing the user's motion patterns, resulting in inadequate exploitation of user preferences. Besides, the majority of prior studies often neglect high-order neighborhood information in users' check-in trajectory and their social relationships, yielding suboptimal recommendation efficacy. To address these issues, this paper proposes a novel Double-Layer Attention Network model, named DLAN. Firstly, DLAN incorporates a multi-head attention module that can combine first-order and high-order neighborhood information in user check-in trajectories, thereby effectively and parallelly capturing both long- and short-term preferences of users and overcoming the problem that RNN-based methods cannot establish long-term dependencies between sequences. Secondly, this paper designs a user similarity weighting layer to measure the influence of other users on the target users leverage the social relationships among them. Finally, comprehensive experiments are conducted on user check-in data from two cities, New York (NYC) and Tokyo (TKY), and the results demonstrate that DLAN achieves a performance in Accuracy and Mean Reverse Rank enhancement by 8.07% -36.67% compared to the state-of-the-art method. Moreover, to investigate the effect of dimensionality and the number of heads of the multi-head attention mechanism on the performance of the DLAN model, we have done sufficient sensitivity experiments. [ABSTRACT FROM AUTHOR]

Monocular depth estimation using a single remote sensing image has emerged as a focal point in both remote sensing and computer vision research, proving crucial in tasks such as 3D reconstruction and target instance segmentation. Monocular depth estimation does not require multiple views as references, leading to significant improvements in both time and efficiency. Due to the complexity, occlusion, and uneven depth distribution of remote sensing images, there are currently few monocular depth estimation methods for remote sensing images. This paper proposes an approach to remote sensing monocular depth estimation that integrates an attention mechanism while considering global and local feature information. Leveraging a single remote sensing image as input, the method outputs end-to-end depth estimation for the corresponding area. In the encoder, the proposed method employs a dense neural network (DenseNet) feature extraction module with efficient channel attention (ECA), enhancing the capture of local information and details in remote sensing images. In the decoder stage, this paper proposes a dense atrous spatial pyramid pooling (DenseASPP) module with channel and spatial attention modules, effectively mitigating information loss and strengthening the relationship between the target's position and the background in the image. Additionally, weighted global guidance plane modules are introduced to fuse comprehensive features from different scales and receptive fields, finally predicting monocular depth for remote sensing images. Extensive experiments on the publicly available WHU-OMVS dataset demonstrate that our method yields better depth results in both qualitative and quantitative metrics. [ABSTRACT FROM AUTHOR]

Regularly detect the corrosion of metal structures and take countermeasures according to the degree of corrosion, which can reduce the potential safety hazards and avoid unnecessary economic losses. This paper presents a deep learning-based metal corrosion detection method, which is used to accurately segment the corrosion regions. This model incorporates Hybrid Attention Residual Block (HARB) and External Skip Connections (ESC) in the basic architecture of U-Net. HARB can reweight the features so that the network pays more attention to the corrosion regions and ignores other irrelevant regions. Shallow features and deep features are fused using ESC to make the features of network learning more effective and comprehensive, which is conducive to improving the segmentation accuracy. In order to further improve the semantic segmentation performance, the Attention Gate Residual Block (AGRB) is proposed, which can optimize segmentation by strengthening the regions to be segmented and reducing the activation value of the background, while overcoming the semantic and scale inconsistencies between input features. In this paper, comprehensive comparative experiments are conducted on the Metal Corrosion dataset. The experimental results show that the F1 and mIoU of the proposed method are 91.21% and 89.56%, respectively. Compared with U-Net, HEU-Net achieves a 7.91% improvement in F1 and a 10.16% improvement in mIoU. These results show that our method outperforms state-of-the-art models and can achieve better semantic segmentation results. [ABSTRACT FROM AUTHOR]

This paper argues for a greater theorization of "place" within aging-in-place research. It extends calls for a relational conceptualization of place by demonstrating the need for aging-in-place researchers to also pay greater attention to territorial aspects of place. This complementary understanding will help establish a new spatial grammar within aging-in-place research, that not only would improve conceptual clarity to aging in place, but would also support a more critical engagement of aging in place in questions of inequality. The paper demonstrates this through a discussion of 2 forms of inequality pertinent to older people: the uneven capacity of places to support older people and experiences of social exclusion in relation to place attachment for older people from marginalized groups. [ABSTRACT FROM AUTHOR]