TransConv: Transformer Meets Contextual Convolution for Unsupervised Domain Adaptation.

Unsupervised domain adaptation (UDA) aims to reapply the classifier to be ever-trained on a labeled source domain to a related unlabeled target domain. Recent progress in this line has evolved with the advance of network architectures from convolutional neural networks (CNNs) to transformers or both hybrids. However, this advance has to pay the cost of high computational overheads or complex training processes. In this paper, we propose an efficient alternative hybrid architecture by marrying transformer to contextual convolution (TransConv) to solve UDA tasks. Different from previous transformer based UDA architectures, TransConv has two special aspects: (1) reviving the multilayer perception (MLP) of transformer encoders with Gaussian channel attention fusion for robustness, and (2) mixing contextual features to highly efficient dynamic convolutions for cross-domain interaction. As a result, TransConv enables to calibrate interdomain feature semantics from the global features and the local ones. Experimental results on five benchmarks show that TransConv attains remarkable results with high efficiency as compared to the existing UDA methods.

The effect of task load, information reliability and interdependency on anticipation performance.

In sport, coaches often explicitly provide athletes with stable contextual information related to opponent action preferences to enhance anticipation performance. This information can be dependent on, or independent of, dynamic contextual information that only emerges during the sequence of play (e.g. opponent positioning). The interdependency between contextual information sources, and the associated cognitive demands of integrating information sources during anticipation, has not yet been systematically examined. We used a temporal occlusion paradigm to alter the reliability of contextual and kinematic information during the early, mid- and final phases of a two-versus-two soccer anticipation task. A dual-task paradigm was incorporated to investigate the impact of task load on skilled soccer players' ability to integrate information and update their judgements in each phase. Across conditions, participants received no contextual information (control) or stable contextual information (opponent preferences) that was dependent on, or independent of, dynamic contextual information (opponent positioning). As predicted, participants used reliable contextual and kinematic information to enhance anticipation. Further exploratory analysis suggested that increased task load detrimentally affected anticipation accuracy but only when both reliable contextual and kinematic information were available for integration in the final phase. This effect was observed irrespective of whether the stable contextual information was dependent on, or independent of, dynamic contextual information. Findings suggest that updating anticipatory judgements in the final phase of a sequence of play based on the integration of reliable contextual and kinematic information requires cognitive resources.

A Dilated Convolutional Neural Network for Cross-Layers of Contextual Information for Congested Crowd Counting.

Crowd counting is an important task that serves as a preprocessing step in many applications. Despite obvious improvement reported by various convolutional-neural-network-based approaches, they only focus on the role of deep feature maps while neglecting the importance of shallow features for crowd counting. In order to surmount this issue, a dilated convolutional-neural-network-based cross-level contextual information extraction network is proposed in this work, which is abbreviated as CL-DCNN. Specifically, a dilated contextual module (DCM) is constructed by importing cross-level connection between different feature maps. It can effectively integrate contextual information while conserving the local details of crowd scenes. Extensive experiments show that the proposed approach outperforms state-of-the-art approaches using five public datasets, i.e., ShanghaiTech part A, ShanghaiTech part B, Mall, UCF_CC_50 and UCF-QNRF, achieving MAE 52.6, 8.1, 1.55, 181.8, and 96.4, respectively.

SCAN: sequence-based context-aware association network for hepatic vessel segmentation.

Accurate segmentation of hepatic vessel is significant for the surgeons to design the preoperative planning of liver surgery. In this paper, a sequence-based context-aware association network (SCAN) is designed for hepatic vessel segmentation, in which three schemes are incorporated to simultaneously extract the 2D features of hepatic vessels and capture the correlations between adjacent CT slices. The two schemes of slice-level attention module and graph association module are designed to bridge feature gaps between the encoder and the decoder in the low- and high-dimensional spaces. The region-edge constrained loss is designed to well optimize the proposed SCAN, which integrates cross-entropy loss, dice loss, and edge-constrained loss. Experimental results indicate that the proposed SCAN is superior to several existing deep learning frameworks, in terms of 0.845 DSC, 0.856 precision, 0.866 sensitivity, and 0.861 F1-score.

"What we talk about is creating a probability": Exploring the interaction between the anticipation and decision-making processes of professional bowlers and batters in Twenty20 cricket.

Expert performers in time constrained sports use a range of information sources to facilitate anticipatory and decision-making processes. However, research has often focused on responders such as batters, goalkeepers, defenders, and returners of serve, and failed to capture the complex interaction between opponents, where responders can also manipulate probabilities in their favour. This investigation aimed to explore the interaction between top order batters and fast or medium paced bowlers in cricket and the information they use to inform their anticipatory and decision-making skills in Twenty20 competition. Eleven professional cricketers were interviewed (8 batters and 3 bowlers) using semi-structured questions and scenarios from Twenty20 matches. An inductive and deductive thematic analysis was conducted using the overarching themes of Situation Awareness (SA) and Option Awareness (OA). Within SA, the sub-themes identified related to information sources used by bowlers and batters (i.e., stable contextual information, dynamic contextual information, kinematic information). Within OA, the sub-themes identified highlighted how cricketers use these information sources to understand the options available and the likelihood of success associated with each option (e.g., risk and reward, personal strengths). A sub-theme of 'responder manipulation' was also identified within OA to provide insight into how batters and bowlers interact in a cat-and-mouse like manner to generate options that manipulate one another throughout the competition. A schematic has been developed based on the study findings to illustrate the complex interaction between the anticipation and decision-making processes of professional top order batters and fast or medium paced bowlers in Twenty20 cricket.

A Heart Image Segmentation Method Based on Position Attention Mechanism and Inverted Pyramid.

In the realm of modern medicine, medical imaging stands as an irreplaceable pillar for accurate diagnostics. The significance of precise segmentation in medical images cannot be overstated, especially considering the variability introduced by different practitioners. With the escalating volume of medical imaging data, the demand for automated and efficient segmentation methods has become imperative. This study introduces an innovative approach to heart image segmentation, embedding a multi-scale feature and attention mechanism within an inverted pyramid framework. Recognizing the intricacies of extracting contextual information from low-resolution medical images, our method adopts an inverted pyramid architecture. Through training with multi-scale images and integrating prediction outcomes, we enhance the network's contextual understanding. Acknowledging the consistent patterns in the relative positions of organs, we introduce an attention module enriched with positional encoding information. This module empowers the network to capture essential positional cues, thereby elevating segmentation accuracy. Our research resides at the intersection of medical imaging and sensor technology, emphasizing the foundational role of sensors in medical image analysis. The integration of sensor-generated data showcases the symbiotic relationship between sensor technology and advanced machine learning techniques. Evaluation on two heart datasets substantiates the superior performance of our approach. Metrics such as the Dice coefficient, Jaccard coefficient, recall, and F-measure demonstrate the method's efficacy compared to state-of-the-art techniques. In conclusion, our proposed heart image segmentation method addresses the challenges posed by diverse medical images, offering a promising solution for efficiently processing 2D/3D sensor data in contemporary medical imaging.

SFHG-YOLO: A Simple Real-Time Small-Object-Detection Method for Estimating Pineapple Yield from Unmanned Aerial Vehicles.

The counting of pineapple buds relies on target recognition in estimating pineapple yield using unmanned aerial vehicle (UAV) photography. This research proposes the SFHG-YOLO method, with YOLOv5s as the baseline, to address the practical needs of identifying small objects (pineapple buds) in UAV vision and the drawbacks of existing algorithms in terms of real-time performance and accuracy. Field pineapple buds are small objects that may be detected in high density using a lightweight network model. This model enhances spatial attention and adaptive context information fusion to increase detection accuracy and resilience. To construct the lightweight network model, the first step involves utilizing the coordinate attention module and MobileNetV3. Additionally, to fully leverage feature information across various levels and enhance perception skills for tiny objects, we developed both an enhanced spatial attention module and an adaptive context information fusion module. Experiments were conducted to validate the suggested algorithm's performance in detecting small objects. The SFHG-YOLO model exhibited significant gains in assessment measures, achieving mAP@0.5 and mAP@0.5:0.95 improvements of 7.4% and 31%, respectively, when compared to the baseline model YOLOv5s. Considering the model size and computational cost, the findings underscore the superior performance of the suggested technique in detecting high-density small items. This program offers a reliable detection approach for estimating pineapple yield by accurately identifying minute items.

Context-aware driver risk prediction with telematics data.

Driving risk prediction is crucial for safety and risk mitigation. While traditional methods rely on demographic information for insurance pricing, they may not fully capture actual driving behavior. To address this, telematics data has gained popularity. This study focuses on using telematics data and contextual information (e.g., road type, daylight) to represent a driver's style through tensor representations. Drivers with similar behaviors are identified by clustering their representations, forming risk cohorts. Past at-fault traffic accidents and citations serve as partial risk labels. The relative magnitude of average records (per driver) for each cohort indicates their risk label, such as low or high risk, which can be transferred to drivers in a cohort. A classifier is then constructed using augmented risk labels and driving style representations to predict driving risk for new drivers. Real-world data from major US cities validates the effectiveness of this framework. The approach is practical for large-scale scenarios as the data can be obtained at scale. Its focus on driver-based risk prediction makes it applicable to industries like auto-insurance. Beyond personalized premiums, the framework empowers drivers to assess their driving behavior in various contexts, facilitating skill improvement over time.

Strategies to Assess Occupational Exposure to Airborne Nanoparticles: Systematic Review and Recommendations.

In many industrial sectors, workers are exposed to manufactured or unintentionally emitted airborne nanoparticles (NPs). To develop prevention and enhance knowledge surrounding exposure, it has become crucial to achieve a consensus on how to assess exposure to airborne NPs by inhalation in the workplace. Here, we review the literature presenting recommendations on assessing occupational exposure to NPs. The 23 distinct strategies retained were analyzed in terms of the following points: target NPs, objectives, steps, "measurement strategy" (instruments, physicochemical analysis, and data processing), "contextual information" presented, and "work activity" analysis. The robustness (consistency of information) and practical aspects (detailed methodology) of each strategy were estimated. The objectives and methodological steps varied, as did the measurement techniques. Strategies were essentially based on NPs measurement, but improvements could be made to better account for "contextual information" and "work activity". Based on this review, recommendations for an operational strategy were formulated, integrating the work activity with the measurement to provide a more complete assessment of situations leading to airborne NP exposure. These recommendations can be used with the objective of producing homogeneous exposure data for epidemiological purposes and to help improve prevention strategies.

CPPVec: an accurate coding potential predictor based on a distributed representation of protein sequence.

Long non-coding RNAs (lncRNAs) play a crucial role in numbers of biological processes and have received wide attention during the past years. Since the rapid development of high-throughput transcriptome sequencing technologies (RNA-seq) lead to a large amount of RNA data, it is urgent to develop a fast and accurate coding potential predictor. Many computational methods have been proposed to address this issue, they usually exploit information on open reading frame (ORF), protein sequence, k-mer, evolutionary signatures, or homology. Despite the effectiveness of these approaches, there is still much room to improve. Indeed, none of these methods exploit the contextual information of RNA sequence, for example, k-mer features that counts the occurrence frequencies of continuous nucleotides (k-mer) in the whole RNA sequence cannot reflect local contextual information of each k-mer. In view of this shortcoming, here, we present a novel alignment-free method, CPPVec, which exploits the contextual information of RNA sequence for coding potential prediction for the first time, it can be easily implemented by distributed representation (e.g., doc2vec) of protein sequence translated from the longest ORF. The experimental findings demonstrate that CPPVec is an accurate coding potential predictor and significantly outperforms existing state-of-the-art methods.

Efficient Approach to Color Image Segmentation Based on Multilevel Thresholding Using EMO Algorithm by Considering Spatial Contextual Information.

The process of image segmentation is partitioning an image into its constituent parts and is a significant approach for extracting interesting features from images. Over a couple of decades, many efficient image segmentation approaches have been formulated for various applications. Still, it is a challenging and complex issue, especially for color image segmentation. To moderate this difficulty, a novel multilevel thresholding approach is proposed in this paper based on the electromagnetism optimization (EMO) technique with an energy curve, named multilevel thresholding based on EMO and energy curve (MTEMOE). To compute the optimized threshold values, Otsu's variance and Kapur's entropy are deployed as fitness functions; both values should be maximized to locate optimal threshold values. In both Kapur's and Otsu's methods, the pixels of an image are classified into different classes based on the threshold level selected on the histogram. Optimal threshold levels give higher efficiency of segmentation; the EMO technique is used to find optimal thresholds in this research. The methods based on an image's histograms do not possess the spatial contextual information for finding the optimal threshold levels. To abolish this deficiency an energy curve is used instead of the histogram and this curve can establish the spatial relationship of pixels with their neighbor pixels. To study the experimental results of the proposed scheme, several color benchmark images are considered at various threshold levels and compared with other meta-heuristic algorithms: multi-verse optimization, whale optimization algorithm, and so on. The investigational results are illustrated in terms of mean square error, peak signal-to-noise ratio, the mean value of fitness reach, feature similarity, structural similarity, variation of information, and probability rand index. The results reveal that the proposed MTEMOE approach overtops other state-of-the-art algorithms to solve engineering problems in various fields.

Deep multi-modal intermediate fusion of clinical record and time series data in mortality prediction.

In intensive care units (ICUs), mortality prediction is performed by combining information from these two sources of ICU patients by monitoring patient health. Respectively, time series data generated from each patient admission to the ICU and clinical records consisting of physician diagnostic summaries. However, existing mortality prediction studies mainly cascade the multimodal features of time series data and clinical records for prediction, ignoring thecross-modal correlation between the underlying features in different modal data. To address theseissues, we propose a multimodal fusion model for mortality prediction that jointly models patients' time-series data as well as clinical records. We apply a fine-tuned Bert model (Bio-Bert) to the patient's clinical record to generate a holistic embedding of the text part, which is then combined with the output of an LSTM model encoding the patient's time-series data to extract valid features. The global contextual information of each modal data is extracted using the improved fusion module to capture the correlation between different modal data. Furthermore, the improved fusion module can be easily added to the fusion features of any unimodal network and utilize existing pre-trained unimodal model weights. We use a real dataset containing 18904 ICU patients to train and evaluate our model, and the research results show that the representations obtained by themodel can achieve better prediction accuracy compared to the baseline.

The Use of Contextual Information for Anticipation of Badminton Shots in Different Expertise Levels.

Purpose: The current study investigated the use of contextual information for anticipation in badminton. Method: Participants were groups of elites (n = 26), competitive (n = 15) and novice players (n = 17) whose anticipation accuracy and reaction time were assessed using an ecologically valid badminton specific video-based occlusion test. Two conditions were presented, where either only kinematic information was available (Last Strokes condition, LS), or kinematic and contextual information were both available (Full Rally condition, FR). Results: Participants reacted slower in the FR condition, while no differences in accuracy were observed between the two conditions. Furthermore, all participants were better at side predictions than length, and elites outperformed novices in both side and length predictions. Among the elite group (which was split into adult elites, adult sub-elites & young elites), adult elite athletes showed faster responses for both the LS and FR conditions compared to their other elite counterparts who were much slower in both conditions. Conclusion: These results indicate that even at the highest level, anticipation performance can discriminate between groups of expert performers. In addition, the findings of this study indicate that the role of contextual information might not be as large as hypothesized, and further research is needed to clarify the role of contextual information toward anticipation.

Reliance upon contextual information can impede visual anticipation.

This study investigated whether skilled batsmen in a state cricket pathway could anticipate ball types when congruency of field-placings was manipulated with a bowler's action. Twenty-four male cricket batsmen were recruited who had played either first-class cricket (n = 6), were part of under 17 (n = 8) or under 19 (n = 10) state cricket squads. Participants completed a video-based temporal occlusion test where they were required to anticipate ball types from a swing bowler. In condition one, contextual field-placing information was presented to be congruent with the delivery type and bowler's action, whilst in condition two it was incongruent. Results did not reveal skill level differences across conditions for anticipation. In the congruent condition, all skill groups predicted above the chance level at the beginning and end of the bowler's delivery stride. In the incongruent condition, first-class players predicted above chance at the beginning of the bowler's delivery stride, and to a higher magnitude above chance compared to other skill groups at ball release. Under 17 and 19 players could not predict above chance at the start of the bowler's delivery stride with their magnitude of prediction lower than first-class players at ball release. Results indicate skilled batsmen find it challenging to integrate contextual and kinematic information to anticipate. This is likely due to greater emphasis placed upon contextual information in part supplied by data analysts. Findings have theoretical and practical implications respectively for lower body positioning for bat-ball interception and perceptual training to improve pick-up of kinematic cues.HIGHLIGHTSSkilled batsmen in a high-performance state cricket pathway could integrate congruent field-placings and bowler kinematics to anticipate ball types.First-class batsmen could integrate incongruent field-placing information to the start, but not the end, of the bowler's delivery action to anticipate ball types.Under 17 and 19 batsmen could not integrate incongruent field-placings to bowler kinematics to anticipate ball types.Skilled batsmen who cannot use kinematic information to anticipate ball types should be given visual-perceptual simulation training to accelerate performance.

MLCA2F: Multi-Level Context Attentional Feature Fusion for COVID-19 lesion segmentation from CT scans.

In the field of diagnosis and treatment planning of Coronavirus disease 2019 (COVID-19), accurate infected area segmentation is challenging due to the significant variations in the COVID-19 lesion size, shape, and position, boundary ambiguity, as well as complex structure. To bridge these gaps, this study presents a robust deep learning model based on a novel multi-scale contextual information fusion strategy, called Multi-Level Context Attentional Feature Fusion (MLCA2F), which consists of the Multi-Scale Context-Attention Network (MSCA-Net) blocks for segmenting COVID-19 lesions from Computed Tomography (CT) images. Unlike the previous classical deep learning models, the MSCA-Net integrates Multi-Scale Contextual Feature Fusion (MC2F) and Multi-Context Attentional Feature (MCAF) to learn more lesion details and guide the model to estimate the position of the boundary of infected regions, respectively. Practically, extensive experiments are performed on the Kaggle CT dataset to explore the optimal structure of MLCA2F. In comparison with the current state-of-the-art methods, the experiments show that the proposed methodology provides efficient results. Therefore, we can conclude that the MLCA2F framework has the potential to dramatically improve the conventional segmentation methods for assisting clinical decision-making.

Panoptic blind image inpainting.

In autonomous driving, scene understanding is a critical task in recognizing the driving environment or dangerous situations. Here, a variety of factors, including foreign objects on the lens, cloudy weather, and light blur, often reduce the accuracy of scene recognition. In this paper, we propose a new blind image inpainting model that accurately reconstructs images in a real environment where there is no ground truth for restoration. To this end, we first introduce a panoptic map to represent content information in detail and design an encoder-decoder structure to predict the panoptic map and the corrupted region mask. Then, we construct an image inpainting model that utilizes the information of the predicted map. Lastly, we present a mask refinement process to improve the accuracy of map prediction. To evaluate the effectiveness of the proposed model, we compared the restoration results of various inpainting methods on the cityscapes and coco datasets. Experimental results show that the proposed model outperforms other blind image inpainting models in terms of L1/L2 losses, PSNR and SSIM, and achieves similar performance to other image inpainting techniques that utilize additional information.

Contextual information in medicolegal death investigation decision-making: Manner of death determination for cases of a single gunshot wound.

To explore the role of contextual information in determining manner of death, four cases involving single gunshot wounds were presented to participants (n = 252) involved in medicolegal death investigation. The participants received identical autopsy information but different contextual information. The data demonstrated that participants tended to rely on contextual information more than autopsy information: In the suicide context, participants across the four cases reached 153 final decisions of suicide (and 25 of homicide), whereas in the homicide context, participants reached only 10 final decisions of suicide (and 181 of homicide) --all while examining identical autopsy information. The impact of the contextual information was so powerful that many participants changed initial autopsy-based conclusions to align with the contextual information. Given the significant role and impact that contextual information has on expert decision making, one must consider what, how, and when contextual information should be used.

VANet: a medical image fusion model based on attention mechanism to assist disease diagnosis.

BACKGROUND: Today's biomedical imaging technology has been able to present the morphological structure or functional metabolic information of organisms at different scale levels, such as organ, tissue, cell, molecule and gene. However, different imaging modes have different application scope, advantages and disadvantages. In order to improve the role of medical image in disease diagnosis, the fusion of biomedical image information at different imaging modes and scales has become an important research direction in medical image. Traditional medical image fusion methods are all designed to measure the activity level and fusion rules. They are lack of mining the context features of different modes of image, which leads to the obstruction of improving the quality of fused images. METHOD: In this paper, an attention-multiscale network medical image fusion model based on contextual features is proposed. The model selects five backbone modules in the VGG-16 network to build encoders to obtain the contextual features of medical images. It builds the attention mechanism branch to complete the fusion of global contextual features and designs the residual multiscale detail processing branch to complete the fusion of local contextual features. Finally, it completes the cascade reconstruction of features by the decoder to obtain the fused image. RESULTS: Ten sets of images related to five diseases are selected from the AANLIB database to validate the VANet model. Structural images are derived from MR images with high resolution and functional images are derived from SPECT and PET images that are good at describing organ blood flow levels and tissue metabolism. Fusion experiments are performed on twelve fusion algorithms including the VANet model. The model selects eight metrics from different aspects to build a fusion quality evaluation system to complete the performance evaluation of the fused images. Friedman's test and the post-hoc Nemenyi test are introduced to conduct professional statistical tests to demonstrate the superiority of VANet model. CONCLUSIONS: The VANet model completely captures and fuses the texture details and color information of the source images. From the fusion results, the metabolism and structural information of the model are well expressed and there is no interference of color information on the structure and texture; in terms of the objective evaluation system, the metric value of the VANet model is generally higher than that of other methods.; in terms of efficiency, the time consumption of the model is acceptable; in terms of scalability, the model is not affected by the input order of source images and can be extended to tri-modal fusion.

A new classification network for diagnosing Alzheimer's disease in class-imbalance MRI datasets.

Automatic identification of Alzheimer's Disease (AD) through magnetic resonance imaging (MRI) data can effectively assist to doctors diagnose and treat Alzheimer's. Current methods improve the accuracy of AD recognition, but they are insufficient to address the challenge of small interclass and large intraclass differences. Some studies attempt to embed patch-level structure in neural networks which enhance pathologic details, but the enormous size and time complexity render these methods unfavorable. Furthermore, several self-attention mechanisms fail to provide contextual information to represent discriminative regions, which limits the performance of these classifiers. In addition, the current loss function is adversely affected by outliers of class imbalance and may fall into local optimal values. Therefore, we propose a 3D Residual RepVGG Attention network (ResRepANet) stacked with several lightweight blocks to identify the MRI of brain disease, which can also trade off accuracy and flexibility. Specifically, we propose a Non-local Context Spatial Attention block (NCSA) and embed it in our proposed ResRepANet, which aggregates global contextual information in spatial features to improve semantic relevance in discriminative regions. In addition, in order to reduce the influence of outliers, we propose a Gradient Density Multiple-weighting Mechanism (GDMM) to automatically adjust the weights of each MRI image via a normalizing gradient norm. Experiments are conducted on datasets from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Australian Imaging, Biomarker and Lifestyle Flagship Study of Aging (AIBL). Experiments on both datasets show that the accuracy, sensitivity, specificity, and Area Under the Curve are consistently better than for state-of-the-art methods.

Transmission Line Object Detection Method Based on Contextual Information Enhancement and Joint Heterogeneous Representation.

Transmission line inspection plays an important role in maintaining power security. In the object detection of the transmission line, the large-scale gap of the fittings is still a main and negative factor in affecting the detection accuracy. In this study, an optimized method is proposed based on the contextual information enhancement (CIE) and joint heterogeneous representation (JHR). In the high-resolution feature extraction layer of the Swin transformer, the convolution is added in the part of the self-attention calculation, which can enhance the contextual information features and improve the feature extraction ability for small objects. Moreover, in the detection head, the joint heterogeneous representations of different detection methods are combined to enhance the features of classification and localization tasks, which can improve the detection accuracy of small objects. The experimental results show that this optimized method has a good detection performance on the small-sized and obscured objects in the transmission line. The total mAP (mean average precision) of the detected objects by this optimized method is increased by 5.8%, and in particular, the AP of the normal pin is increased by 18.6%. The improvement of the accuracy of the transmission line object detection method lays a foundation for further real-time inspection.