Representation Of Categories Research Articles

MATNet: A Combining Multi-Attention and Transformer Network for Hyperspectral Image Classification

Hyperspectral image (HSI) has rich spatial-spectral information, high spectral correlation and large redundancy between information. Due to the sparse background distribution of HSI, existing methods generally perform poorly for the classification of class pixels located in the boundary areas of land cover categories. This is largely because the network is vulnerable to surrounding redundant information during the training stage, leading to inaccurate feature extraction and thus poor generalization ability of the model. Based on previous work, we propose a HSI classification network called MATNet which combines multi-attention and Transformer. The network first uses spatial attention and channel attention to pay more attention to the more significant information parts, then uses tokenizer module to make a semantic level representation of different categories of ground objects, and then performs deep semantic feature extraction using the transformer encoder module. Finally, we design a loss function called Lpoly, which adds a polynomial to the label smoothing loss to tune the original first polynomial to accommodate different datasets and tasks. We perform experiments in several well-known HSI datasets as well as for visualization. The results show that our proposed MATNet performs well in extracting spatial-spectral features of HSIs as well as understanding semantic degrees of semantic degrees.

Category Knowledge-guided Parameter Calibration for Few-shot Object Detection.

Few-shot object detection (FSOD) aims to adapt generic detectors to the novel categories with only a few annotations, which is an important and realistic task. Although the generic object detection has been widely studied over the past years, the FSOD is under explored. In this paper, we propose a novel Category Knowledge-guided Parameter Calibration (CKPC) framework to solve the FSOD task. We first propagate the category relation information to explore the representative category knowledge. Then, we explore the RoI-RoI and RoI-Category relations to capture the local-global context information to enhance the RoI (Region of Interest) features. Next, we project the knowledge representations of foreground categories into a parameter space by a linear transformation to generate the parameters of the category-level classifier. For the background, we learn a proxy category by concluding the global characteristics of all foreground categories to help ensure the discrepancy between the foreground and background, which is then projected into the parameter space by the same linear transformation. Finally, we leverage the parameters of the category-level classifier to explicitly calibrate the instance-level classifier learned on the enhanced RoI features for both the foreground and background categories to improve the detection performance. We conduct extensive experiments on two popular FSOD benchmarks (i.e., Pascal VOC and MS COCO), and the experimental results show that the proposed framework can outperform state-of-the-art methods.

Study to Assess the Knowledge of Hospital Waste Management among Healthcare Personnel at Medical College in Haryana

Background: Hospital Waste collection and proper disposal has become a significant concern for both the medicaland general community. It is estimated that 10-25% of healthcare waste is hazardous, with the potential to createa variety of health problems. Handling, segregation, mutilation, disinfection, storage, transportation and finaldisposal are vital steps for safe and scientific management of Hospital waste in any establishment.Objectives: To assess the knowledge of hospital Waste management among healthcare personnel working in atertiary care centre.Methods: To assess the knowledge of hospital Waste management among healthcare personnel working in atertiary care hospital. A hospital based cross sectional study was conducted. The Study participants includednursing staff, ward boys and cleaning staff working in the institute who deal with Medical waste and were selectedrandomly to make the sample size of 250 with equal representation in both categories. A pretested semi-structuredquestionnaire was used.Results: The study showed gaps in the knowledge of categories of respondents. The knowledge of the existence ofMedical waste management in nurses was (79%), as well as in cleaning staff was (37%). The knowledge in practicalaspects of Medical waste management was better in nurses, as compare to cleaning staff.

Class Centralized Dictionary Learning for Few-Shot Remote Sensing Scene Classification

Recently, few-shot scene classification has become an important task in the remote sensing (RS) field, mainly solving how to obtain better classification performance when there are insufficient labeled samples. The few-shot scene classification task includes the pretrain stage and meta-test stage. There is no category intersection between these two stages. Thus, the sample distribution of the training set and meta-test set is different, leading to the training model’s weak generalization or portability. To solve this problem, we propose a class-centralized dictionary learning (CCDL) method for the few-shot RS scene classification (FSRSSC). Specifically, in the pretraining stage, we adopt the model pretrained on a large natural images dataset and then fine-tune the network by the RS dataset. Using the pretrained model helps improve the model’s generalization ability. In the meta-test stage, we propose a CCDL classifier, which guarantees the sparse representations of different categories more distant and the same more concentrated. We experiment on several benchmark datasets and achieve superior performance, demonstrating the proposed method’s effectiveness.

STATUS CATEGÓRICO E SEUS MECANISMOS RELACIONAIS DE ORDENAÇÃO DOS MERCADOS

ABSTRACT Status systems bring social order to markets, but they are non-meritocratic arrangements that benefit those of a higher status and penalize those of a lower status. Paradoxically, these systems are also maintained by those who suffer the most from their inequalities. The literature tends to explain the persistence of these systems through macro-oriented or micro-oriented mechanisms. We propose an alternative path by investigating relational mechanisms that might explain the persistence of this paradox. In an haute cuisine market, we used the social network analysis perspective to identify relational mechanisms that maintain this collective system. The results revealed a three-role structure of symbolic deference/appreciation (diffuse, selective, and egocentric). To conclude, we highlight the social order as a continuous tension between normality and chaos in the relationships between roles and the procedural aspect of structuring market roles, which we call authorizing the representation of a market category.

Category-Aware Multimodal Attention Network for Fashion Compatibility Modeling

Fashion compatibility modeling, which is used to estimate the matching degree of a given set of fashion items, has received increasing attention in recent years. However, existing studies often fail to fully leverage multimodal information or ignore the semantic guidance of clothing categories in elevating the reliability of multimodal information. In this paper, we propose a fashion compatibility modeling approach with a category-aware multimodal attention network, termed as FCM-CMAN. In FCM-CMAN, we focus on enriching and aggregating multimodal representations of fashion items by means of the dynamic representations of categories and a contextual attention mechanism simultaneously. Specifically, considering that category correlations are always dynamic and varied for different fashion items, we design a categorical dynamic graph convolutional network to adaptively learn the semantic correlations between categories. When combined with the multi-layered visual outputs of a convolutional neural network and the surrounding contextual information, multiple content-aware category representations and context-aware attention weights are obtained to better characterize fashion items from different aspects. On this basis, two pieces of aware information are integrated by a multimodal factorized bilinear pooling strategy to generate visual-semantic embeddings, which are further improved by a multi-head self-attention mechanism to capture significant elements related to fashion compatibility. Extensive experiments conducted on the FashionVC and ExpFashion datasets demonstrate the superiority of FCM-CMAN over state-of-the-art methods.

ОККАЗИОНАЛЬНОЕ СЛОВООБРАЗОВАНИЕ: КОГНИТИВНО-ДИСКУРСИВНЫЙ АСПЕКТ

The article considers occasional word formation as a linguistic phenomenon of the intensity category representation in differently structured languages in the light of the cognitive-discursive paradigm of modern linguistic research. This study is based on the principle of synthesizing the accumulated knowledge on the theory and methodology of cognitive-discursive analysis, on the theory and semantics of word formation, including the use of methods of comparative, textological, component, functional-semantic and morphological analysis. Based on the analysis of the precedent poetic texts of the Russian author V. Mayakovsky, the word-formation models of occasional formations in the Russian language are identified and the ways of their reconstruction in the target language (German) are substantiated. The author singles out nominal suffixal occasionalisms (nouns and adjectives), nominal and verbal prefixed occasionalisms and nominal compound occasionalisms according to the word-formation method, highlighting as a separate group grammar occasionalisms (or formative occasional formations). They are characterized by the use of lexical units conventionally fixed in lexicographic publications, while the grammatical forms of these units are non-standardized. Translated German analogues are characterized by both analytical word-building structures, determined by the translator’s desire to convey not only the meaning, but also preserve the original form of translated occasionalism, and the widespread use of the descriptive method of translation, which includes usual lexical units to describe the original occasionalism. The comparison of the Russian and German languages reveals the differences in the semantic, structural and syntactic (rhythmic for poetic discourse) aspects on the example of occasional units of poetic discourse. This indicates the need to talk not about equivalence in translation, but about the correlation of the analyzed units. As a result of comparing the studied units, certain regularities characteristic of the derivational systems of the Russian and German languages, reflecting the cognitive-mental nature of the word-formation processes of categorization and conceptualization of the external and internal world of the Russian and German linguistic culture members were established.

Consensus graph learning-based self-supervised ensemble clustering

目的 随着实际应用场景中海量数据采集技术的发展和数据标注成本的不断增加，自监督学习成为海量数据分析的一个重要策略。然而，如何从海量数据中抽取有用的监督信息，并该监督信息下开展有效的学习仍然是制约该方向发展的研究难点。为此，提出了一个基于共识图学习的自监督集成聚类框架。方法 框架主要包括3个功能模块。首先，利用集成学习中多个基学习器构建共识图；其次，利用图神经网络分析共识图，捕获节点优化表示和节点的聚类结构，并从聚类中挑选高置信度的节点子集及对应的类标签生成监督信息；再次，在此标签监督下，联合其他无标注样本更新集成成员基学习器。交替迭代上述功能块，最终提高无监督聚类的性能。结果 为验证该框架的有效性，在标准数据集（包括图像和文本数据）上设计了一系列实验。实验结果表明，所提方法在性能上一致优于现有聚类方法。尤其是在MNIST-Test （modified national institute of standards and technology database）上，本文方法实现了97.78%的准确率，比已有最佳方法高出3.85%。结论 该方法旨在利用图表示学习提升自监督学习中监督信息捕获的能力，监督信息的有效获取进一步强化了集成学习中成员构建的能力，最终提升了无监督海量数据本质结构的挖掘性能。;Objective Clustering is focused on machine learning-related data segmentation for multiple datasets. Its applications are in relevant to such domains like image segmentation and anomaly detection. In addition，to simplify complex tasks optimize its performance，clustering is used in data preprocessing tasks of those are data sub-blocks segmentation， pseudo-labels generation，and abnormal points-removal. Self-supervised learning has become an essential technique for massive data analysis. However，it is challenged to extract effective supervision information and analyze the input data. Method A consensus graph learning based self-supervised ensemble clustering（CGL-SEC）framework is developed. It consists of three main modules：1）to construct the consensus graph based on several ensemble components（i. e. ，the basic clustering methods）. 2）to extract the supervision information by learning the consensus graph representation，and 3）its node clustering results，where the subset of nodes with the high-confidence are selected as labeled samples. To optimize the ensemble components and the corresponding consensus graph，t basic clustering methods are re-trained in related the option of samples-labeled and other samples-unlabeled. The final clustering results can be optimized iteratively until the learning process converges. Result A series of experiments are carried out on benchmarks，including both image and textual datasets. Especially，CGL-SEC is 3. 85% over baseline in terms of clustering evaluation metric on themodified national institute of standards and technology database（MNIST-Test）. First，to optimize data representation and cluster assignment at the same time，deep embedding clustering can be focused on data itself as the supervision information and auto-encoder with the reconstruction loss is pre-trained. The soft cluster assignment of features-embedded is then calculated，and the KL（Kullback-Leibler）divergence is minimized between the soft cluster assignment and the auxiliary target distribution. To improve the performance of the model further，following deep clustering network（DCN）can use hard clustering instead of soft allocation，and local constraints are applied by improved deep embedding clustering（IDEC）. The pseudo-label strategy is implemented as a self-supervised learning method that uses the prediction results of the neural network as the label to simulate the supervision information compared to using data itself as the supervision information. Deepcluster-based K-means clustering is used to generate pseudo-labels to guide the training of convolutional networks. However，the generated pseudo-labels have lower confidence and are prone to trivial solutions in the initial stage of network training. Deep embedding clustering with data augmentation（DEC-DA）and MixMatch-based prediction of data-enhanced samples are used as the supervision information of the original data，which improves the accuracy of the supervision information to a certain extent，but this method is difficult to extend to text and other fields. Deep adaptive clustering-based high-confidence pseudo-label subsets-selected are iteratively trained the network in the prediction results，but lowconfidence samples-involved data distribution information is ignored. Pseudo-semi-supervised clustering votes are used to select a subset of high-confidence pseudo-labels，and all samples are used to train semi-supervised neural network. Although the ensemble strategy can improve the confidence of the pseudo-label，the voting strategy is concerned of category representation only without the feature representation of the sample itself，which can reduce the clustering performance in some cases. The ensemble learning is regarded as a representative machine learning method that reflects the ability of group intelligence，whereas a learning method can improve the overall prediction performance via multiple base learners training and their coordinated prediction results. In pseudo-label-based clustering tasks，it can coordinate multiple base learners to obtain high-confidence pseudo-labels. However，the effectiveness of the supervision information acquisition is still to be resolved. The category information of the sample is considered for current pseudo-label-based ensemble clustering method only when the label is captured and some effective information are ignored like the feature representation of the sample itself and the clustering structure between samples. Conclusion Graph neural network is composed of content information of nodes and the structural information between nodes at the same time. To design a self-supervised ensemble clustering method based on consensus graph representation learning，it is required to make full use of sample features and relationships between samples in ensemble learning. To obtain higher confidence pseudo-labels as supervised information and improve the performance of self-supervised clustering，it is necessary to mine global and local information at the same time. We illustrate a learnable data ensemble representation through graph neural network. The confidence of pseudo-labels is improved，and the entire model is trained in self-supervision iteratively. To be summarized：1）Commonly-used consensus graph learning-integrated clustering framework is developed，which can use multi-level information like clusteringintegrated sample characteristics and category structure. 2）Self-supervision method is proposed，which uses graph neural network to mine the global and local information of the consensus graph，and high-confidence pseudo-labels are obtained as supervised information. 3）Experiments are demonstrated that the consensus graph learning ensemble clustering method has its potentials on image and text datasets.

Facial typicality and attractiveness reflect an ideal dimension of face structure

Face perception and recognition are important processes for social interaction and communication among humans, so understanding how faces are mentally represented and processed has major implications. At the same time, faces are just some of the many stimuli that we encounter in our everyday lives. Therefore, more general theories of how we represent objects might also apply to faces. Contemporary research on the mental representation of faces has centered on two competing theoretical frameworks that arose from more general categorization research: prototype-based face representation and exemplar-based face representation. Empirically distinguishing between these frameworks is difficult and neither one has been ruled out. In this paper, we advance this area of research in three ways. First, we introduce two additional frameworks for mental representation of categories, varying abstraction and ideal representation, which have not been applied to face perception and recognition before. Second, we fit formal computational models of all four of these theories to human perceptual judgments of the typicality and attractiveness (a strong correlate of typicality) of 100 young adult Caucasian female faces, with the models expressed within a face space derived from facial similarity judgments via multidimensional scaling. Third, we predict the perceived typicality and attractiveness of the faces using these models and compare the predictive performance of each to the empirical data. We found that of all four models, the ideal representation model provided the best account of perceived typicality and attractiveness for the present set of faces, although all models showed discrepancies from the empirical data. These findings demonstrate the relevance of mental categorization processes for representing faces.

Supervised term-category feature weighting for improved text classification

Text classification is a central task in Natural Language Processing (NLP) that aims at categorizing text documents into predefined classes or categories. It requires appropriate features to describe the contents and meaning of text documents, and map them with their target categories. Existing text feature representations rely on a weighted representation of the document terms. Hence, choosing a suitable method for term weighting is of major importance and can help increase the effectiveness of the classification task. In this study, we provide a novel text classification framework for Category-based Feature Engineering titled CFE. It consists of a supervised weighting scheme defined based on a variant of the TF-ICF (Term Frequency-Inverse Category Frequency) model, embedded into three new lean classification approaches: (i) IterativeAdditive (flat), (ii) GradientDescentANN (1-layered), and (iii) FeedForwardANN (2-layered). The IterativeAdditive approach augments each document representation with a set of synthetic features inferred from TF-ICF category representations. It builds a term-category TF-ICF matrix using an iterative and additive algorithm that produces category vector representations and updates until reaching convergence. GradientDescentANN replaces the iterative additive process mentioned previously by computing the term-category matrix using a gradient descent ANN model. Training the ANN using the gradient descent algorithm allows updating the term-category matrix until reaching convergence. FeedForwardANN uses a feed-forward ANN model to transform document representations into the category vector space. The transformed document vectors are then compared with the target category vectors, and are associated with the most similar categories. We have implemented CFE including its three classification approaches, and we have conducted a large battery of tests to evaluate their performance. Experimental results on five benchmark datasets show that our lean approaches mostly improve text classification accuracy while requiring significantly less computation time compared with their deep model alternatives.

ОТРАЖЕНИЕ КАТЕГОРИЙ МИГРАНТОВ В РЕГИОНАЛЬНЫХ СМИ И ВОЗМОЖНОСТЬ ЕГО ВЛИЯНИЯ НА ИХ ИНТЕГРАЦИЮ В ПРИНИМАЮЩЕЕ ОБЩЕСТВО: ПО МАТЕРИАЛАМ КОНТЕНТ-АНАЛИЗА ИНТЕРНЕТ-ИЗДАНИЙ РОСТОВСКОЙ ОБЛАСТИ

Objective of the study: by identifying the representation of various categories of migrants in the media of the Rostov region, to identify the potential impact of the broadcast images of these categories on their (migrants') integration into the host society. The methodological basis of the research was the principles of the selection of information messages in the Internet media, in which the unit of selection is a message that touches on the subject of migrants. When selecting messages, the keywords were not only “migrant” and derivatives of this word, but also contexts that fit the topic of migration: refugees, internally displaced persons, border crossing, etc. At the same time, markers were assigned to each message, characterizing them from the point of view of reflecting the categories of migrants. According to the quantitative indicators of the selected messages – the proportion of messages per each category of migrants and the distribution of these messages during the selection period – the potential impact of images of categories of migrants on their integration into the host community was assessed. Research results. It is revealed that the media of the Rostov region are mainly not aimed at forming images of migrants of various categories. The selection of mass media reports on migrants depends on events that are extraordinary for the region and the regional information space. The highest level of representation was found in the categories: refugees and internally displaced persons; labor migrants; without specifying the goals and/or circumstances of stay in the region. None of the categories of migrants has a stable information coverage during the period of the selection of messages, except for the one in which the category of migrants is not indicated. The image of internally displaced persons and refugees has the greatest potential to influence integration. Prospects of the study. The results of the study can be used to further develop the topic of migration at the regional level.

Investigation of Involvement between Specific Brain Regions and Evaluation Criteria Elements in a Two-Selections Task.

It is essential to understand the neural mechanisms underlying human decision-making. Several studies using traditional analysis have attempted to explain the neural mechanisms associated with decision-making based on abstract rewards. However, brain-decoding research that utilizes the multivoxel pattern analysis (MVPA) method, especially research focusing on decision-making, remains limited. In brain analysis, decoding strategies for multivoxels are required for various decision-making evaluation criteria. This is because in daily life, the human decision-making process makes use of many evaluation criteria. In the present study, we investigated the representation of evaluation criterion categories in a decision-making process using functional magnetic resonance imaging and MVPA. Participants performed a decision-making task that involved choosing a smartphone by referring to four types of evaluation criteria. The regions of interest (ROIs) were the ventromedial prefrontal cortex (vmPFC), nucleus accumbens (NAcc), and insula. Each combination of the four evaluation criteria was analyzed based on a binary classification using MVPA. From the binary classification accuracy obtained from MVPA, the regions that reflected differences in the evaluation criteria among the ROIs were evaluated. The results of the binary classification in the vmPFC and NAcc indicated that these regions can express evaluation criteria in decision-making processes.

Emergent color categorization in a neural network trained for object recognition.

Color is a prime example of categorical perception, yet it is unclear why and how color categories emerge. On the one hand, prelinguistic infants and several animals treat color categorically. On the other hand, recent modeling endeavors have successfully utilized communicative concepts as the driving force for color categories. Rather than modeling categories directly, we investigate the potential emergence of color categories as a result of acquiring visual skills. Specifically, we asked whether color is represented categorically in a convolutional neural network (CNN) trained to recognize objects in natural images. We systematically trained new output layers to the CNN for a color classification task and, probing novel colors, found borders that are largely invariant to the training colors. The border locations were confirmed using an evolutionary algorithm that relies on the principle of categorical perception. A psychophysical experiment on human observers, analogous to our primary CNN experiment, shows that the borders agree to a large degree with human category boundaries. These results provide evidence that the development of basic visual skills can contribute to the emergence of a categorical representation of color.

Disentangling Object Category Representations Driven by Dynamic and Static Visual Input.

Humans can label and categorize objects in a visual scene with high accuracy and speed, a capacity well characterized with studies using static images. However, motion is another cue that could be used by the visual system to classify objects. To determine how motion-defined object category information is processed by the brain in the absence of luminance-defined form information, we created a novel stimulus set of "object kinematograms" to isolate motion-defined signals from other sources of visual information. Object kinematograms were generated by extracting motion information from videos of 6 object categories and applying the motion to limited-lifetime random dot patterns. Using functional magnetic resonance imaging (fMRI) (n = 15, 40% women), we investigated whether category information from the object kinematograms could be decoded within the occipitotemporal and parietal cortex and evaluated whether the information overlapped with category responses to static images from the original videos. We decoded object category for both stimulus formats in all higher-order regions of interest (ROIs). More posterior occipitotemporal and ventral regions showed higher accuracy in the static condition, while more anterior occipitotemporal and dorsal regions showed higher accuracy in the dynamic condition. Further, decoding across the two stimulus formats was possible in all regions. These results demonstrate that motion cues can elicit widespread and robust category responses on par with those elicited by static luminance cues, even in ventral regions of visual cortex that have traditionally been associated with primarily image-defined form processing.SIGNIFICANCE STATEMENT Much research on visual object recognition has focused on recognizing objects in static images. However, motion is a rich source of information that humans might also use to categorize objects. Here, we present the first study to compare neural representations of several animate and inanimate objects when category information is presented in two formats: static cues or isolated dynamic motion cues. Our study shows that, while higher-order brain regions differentially process object categories depending on format, they also contain robust, abstract category representations that generalize across format. These results expand our previous understanding of motion-derived animate and inanimate object category processing and provide useful tools for future research on object category processing driven by multiple sources of visual information.

Representation of naturalistic food categories in the human brain

Studies of the neural response to food pictures have identified responses in food-associated regions, such as the insula, amygdala, and orbitofrontal cortex. However, beyond this domain-specific response, little is known about how finer-grained food categories are represented in the brain. Specifically, are brain responses to food pictures driven more by objective measures of food qualities or by subjective estimates of those qualities? To address this question, we asked 487 participants on Amazon Mechanical Turk to perform an “odd-one-out” triplet task to generate a quantitative measure of the similarity of 36 food images with varying known levels of fat and sugar. We used the data from this task to generate a similarity matrix of these foods, which we then analyzed using Principal Components Analysis and K-means clustering, to identify subjective categories of these foods. Using these emergent categories and a Representational Similarity Analysis approach, we analyzed the neuroimaging data of 61 healthy subjects who viewed pictures of these foods and non-food objects during fMRI. PCA of the online data indicated most of the variance was related to participants’ estimates of how processed the foods were and their sugar content, rather than objective measures of fat, sugar, or caloric content. K-means clustering of this data revealed five emergent food groupings: sweets, fats, starches, fruits, and vegetables. Multivariate hemodynamic responses to food pictures reflected this category structure – and not objective nutritional content – in food-responsive ROIs in the brain, as pattern similarity was significantly greater within vs. between categories in the mid-insula, OFC, amygdala, and ventral striatum. A searchlight analysis also reflected this food-category structure in the responses of bilateral regions of the ventral occipito-temporal cortex. These results reveal a fine-grained representation of food categories in the brain that corresponds more to subjective assessments of food qualities, than to objective food properties.

An abstract categorical decision code in dorsal premotor cortex

The dorsal premotor cortex (DPC) has classically been associated with a role in preparing and executing the physical motor variables during cognitive tasks. While recent work has provided nuanced insights into this role, here we propose that DPC also participates more actively in decision-making. We recorded neuronal activity in DPC while two trained monkeys performed a vibrotactile categorization task, utilizing two partially overlapping ranges of stimulus values that varied on two physical attributes: vibrotactile frequency and amplitude. We observed a broad heterogeneity across DPC neurons, the majority of which maintained the same response patterns across attributes and ranges, coding in the same periods, mixing temporal and categorical dynamics. The predominant categorical signal was maintained throughout the delay, movement periods and notably during the intertrial period. Putting the entire population's data through two dimensionality reduction techniques, we found strong temporal and categorical representations without remnants of the stimuli's physical parameters. Furthermore, projecting the activity of one population over the population axes of the other yielded identical categorical and temporal responses. Finally, we sought to identify functional subpopulations based on the combined activity of all stimuli, neurons, and time points; however, we found that single-unit responses mixed temporal and categorical dynamics and couldn't be clustered. All these point to DPC playing a more decision-related role than previously anticipated.

Categorization learning induced changes in action representations in the macaque STS

Neuroimaging and single cell recordings have demonstrated the presence of STS body category-selective regions (body patches) containing neurons responding to presentation of static bodies and body parts. To date, it remains unclear if these body patches and additional STS regions respond during observation of different categories of dynamic actions and to what extent categorization learning influences representations of observed actions in the STS. In the present study, we trained monkeys to discriminate videos depicting three different actions categories (grasping, touching and reaching) with a forced-choice action categorization task. Before and after categorization training, we performed fMRI recordings while monkeys passively observed the same action videos. At the behavioral level, after categorization training, monkeys generalized to untrained action exemplars, in particular for grasping actions. Before training, uni- and/or multivariate fMRI analyses suggest a broad representation of dynamic action categories in particular in posterior and middle STS. Univariate analysis further suggested action category specific training effects in middle and anterior body patches, face patch ML and posterior STS region MT and FST. Overall, our fMRI experiments suggest a widespread representation of observed dynamic bodily actions in the STS that can be modulated by visual learning, supporting its proposed role in action recognition.

HOW PHYSICALLY ACTIVE ARE SPORTS EXPERTS?

Through their actions and behavior forms, coaches set an example for the athletes they work with, and additionally oblige them to lead a healthy lifestyle, which includes a proper diet and regular physical activity manifested in various forms. The aim of the paper is to compare the categories of physical activities between male and female sports experts. The results of the research showed that 63% of trainers practice high physical activity, and 36% moderate physical activity, with women applying high physical activity by 6.8% more than male sports experts. Observed physical activity is expressed in MET units (metabolic equivalent of task). The analysis of the chi-square test did not show a statistically significant difference in the representation of physical activity categories among male and female sports experts. The observed level of physical activity (light, moderate, heavy, total physical activity), analyzed using the t-test for independent samples, did not show a significant difference between male and female coaches. Keywords: coaches, IPAQ questionnaire, MET-values, lifestyle

Multi-instance learning based on spatial continuous category representation for case-level meningioma grading in MRI images

Multi-instance learning based on spatial continuous category representation for case-level meningioma grading in MRI images

A Multi-View Deep Metric Learning approach for Categorical Representation on mixed data

It is an important and challenging task to represent the categorical values in mixed data as numerical vectors with intrinsic features, by revealing the complex coupling relationships between the categorical values, attributes and samples. The majority of extant studies expose only one particular coupling relationship in depth, or fuse multiple coupling relationships by using shallow learning based on kernels. The former may not fully mine the essential features of the categorical data. The latter typically has some limitations, for example, difficulty in expanding the spatial structure and difficulty in determining the optimal kernel function. Therefore, this paper proposes a Multi-view Deep Metric Learning for Categorical Representation on mixed data (MvDML-CR). Specifically, first, based on the principle of information complementarity, multiple coupled views are extracted from the complex interaction relationships of the categorical data. Then, in each coupled view, a new proxy loss function is designed to build a deep metric learning sub-model with strong separability, which represents the categorical values as numerical vectors with discrimination. Last, we employ the Hilbert–Schmidt independence criterion to maximize the dependency between the views, and then fuse the sub-models trained in the different views to enhance the complementarity and consistency of the categorical representations. Extensive experiments on 34 mixed datasets with diversified characteristics demonstrate that the classification performance of MvDML-CR is significantly improved, compared with the state-of-the-art competitors.