Context Representation Research Articles

Geographical representation and re-selection prospects in party-centred contexts

ABSTRACT Legislators often use parliamentary activities with a constituency focus to win personal votes or local selectorates’ support. However, little is known about whether geographically-targeted activities are an effective strategy to secure a seat in party-centred contexts, i.e. with low electoral incentives and exclusive and centralized selectorates. This study explores how legislators’ attention to local issues affects their re-selection chances and placement on party lists. I argue that the party leadership may consider geographical representation an asset or a liability depending on individual MPs’ roles within parties and the types of parliamentary activities employed, reflecting an intra-party division of labour. Using data from three Italian elections (2006–2013) under closed-list PR and centralized candidate selection, the findings suggest that, in such contexts, party leaders may discourage MPs from representing their geographic constituencies.

An Infrared and Visible Image Fusion Network Based on Res2Net and Multiscale Transformer

The aim of infrared and visible image fusion is to produce a composite image that can highlight the infrared targets and maintain plentiful detailed textures simultaneously. Despite the promising fusion performance of current deep-learning-based algorithms, most fusion algorithms highly depend on convolution operations, which limits their capability to represent long-range contextual information. To overcome this challenge, we design a novel infrared and visible image fusion network based on Res2Net and multiscale Transformer, called RMTFuse. Specifically, we devise a local feature extraction module based on Res2Net (LFE-RN) in which dense connections are adopted to reuse the information that might be lost in convolution operation and a global feature extraction module based on multiscale Transformer (GFE-MT) which is composed of a Transformer module and a global feature integration module (GFIM). The Transformer module extracts the coarse-to-fine semantic features of the source images, while GFIM is used to further aggregate the hierarchical features to strengthen contextual feature representations. Furthermore, we employ the pre-trained VGG-16 network to compute the loss of features with different depths. Massive experiments on mainstream datasets indicate that RMTFuse is superior to the state-of-the-art methods in both subjective and objective assessments.

Genitals on Screen: Extremism and the Crisis of Representation

Abstract The article examines the international phenomenon of extreme art cinema with explicit genital content, with a particular focus on Lukas Moodysson’s A Hole in My Heart (Sweden 2004), Srdan Spasojevic’s A Serbian Film (2010), Michael Winterbottom’s 9 songs (UK 2005), and György Pálfi’s Hungarian Taxidermia (2006). The paper sets up three main understandings of these films, distinguishing between those that lack narrative justification for the in-your-face representation of genitals; films in which the pornographic content is integrated into narratives about a crisis in domestic relations, and, finally, films that use the explicit highlighting of genitals as a cornerstone in allegorical representations of broader social-cultural and political contexts.

Towards a Unified Temporal and Event Logic Paradigm for Multi-Hop Path Reasoning in Knowledge Graphs

Path reasoning in knowledge graphs is a pivotal task for uncovering complex relational patterns and facilitating advanced inference processes. It also holds significant potential in domains such as power electronics, where real-time reasoning over dynamic, evolving data is essential for advancing topology design and application systems. Despite its importance, traditional approaches often encounter substantial limitations when applied to dynamic, time-sensitive scenarios. These models typically fail to adequately capture intricate logical dependencies and demonstrate suboptimal performance in data-constrained environments. To address these challenges, we introduce Path-Reasoning Logic (PRlogic), an innovative framework that seamlessly integrates rule-based logical reasoning with cutting-edge neural network methodologies. PRlogic enhances path inference by leveraging a context-aware logical association network adept at handling temporal and event-driven attributes, enabling improved reasoning for dynamic systems such as IoT-based power electronics and smart grids. This adaptability allows the framework to better accommodate evolving knowledge structures, significantly improving reasoning accuracy under resource-scarce conditions. Furthermore, PRlogic employs a multi-stage refinement strategy, harmonizing logic-based rules with learned contextual representations to achieve heightened robustness and scalability. Comprehensive experiments on widely-recognized benchmark datasets validate the superiority of PRlogic, demonstrating its consistent outperformance of existing models in path reasoning tasks. These results underscore the efficacy of incorporating logic-driven mechanisms into knowledge graph reasoning and highlight PRlogic’s potential as a powerful solution for applications in dynamic data environments.

ManiNeg: Manifestation-guided multimodal pretraining for mammography screening.

Breast cancer poses a significant health threat worldwide. Contrastive learning has emerged as an effective method to extract critical lesion features from mammograms, thereby offering a potent tool for breast cancer screening and analysis. A crucial aspect of contrastive learning is negative sampling, where the selection of hard negative samples is essential for driving representations to retain detailed lesion information. In large-scale contrastive learning applied to natural images, it is often assumed that extracted features can sufficiently capture semantic content, and that each mini-batch inherently includes ideal hard negative samples. However, the unique characteristics of breast lumps challenge these assumptions when dealing with mammographic data. In response, we introduce ManiNeg, a novel approach that leverages manifestations as proxies to select hard negative samples. As a condensed representation of a physician's domain knowledge, manifestations represent observable symptoms or signs of a disease and can provide a robust basis for choosing hard negative samples. This approach benefits from its invariance to model optimization, facilitating efficient sampling. We tested ManiNeg on the task of distinguishing between benign and malignant breast lumps. Our results demonstrate that ManiNeg not only improves representation in both unimodal and multimodal contexts but also offers benefits that extend to datasets beyond the initial pretraining phase. To support ManiNeg and future research endeavors, we have developed the MVKL mammographic dataset. This dataset includes multi-view mammograms, corresponding reports, meticulously annotated manifestations, and pathologically confirmed benign-malignant outcomes for each case. The MVKL dataset and our codes are publicly available at https://github.com/wxwxwwxxx/ManiNeg to foster further research within the community.

PhonemeVec: A Phoneme-Level Contextual Prosody Representation For Speech Synthesis

Recently, fine-grained prosody representations have emerged and attracted growing attention to address the one-to-many problem in text-to-speech (TTS). In this paper, we propose the PhonemeVec, a pre-trained prosody representations with considering the contextual information. To obtain the contextual prosody representations, we improve the data2vec framework according to the characteristics of prosody to extract the PhonemeVec from the low-band mel-spectrogram, and pre-train on a 960 hours Chinese corpus with high quality and diverse pronunciation. PhonemeVec is subsequently integrated into FastSpeech2, supervising the prosody modeling of the text encoder. Experiments conducted on the Blizzard Challenge 2019 dataset show that the integration of PhonemeVec results in the synthesis of more natural speech. Additionally, objective evaluations confirm that the application of PhonemeVec reduces the distortions between the generated speech and original recordings in terms of duration and F0. Audio samples can be found in http://home.ustc.edu.cn/~wsmzzz/PhonemeVec/demo.html.

Diversity in research on the psychology of language: A large-scale examination of sampling bias.

The human capacity for language cannot be fully understood without appreciation of its ability to adapt to startling diversity. Narrow sampling therefore undermines the psycholinguistic enterprise. Concerns regarding a lack of sample diversity in psycholinguistics are increasingly being raised, but large-scale data on the state of the field remain absent. In the current paper, we address this empirical gap by documenting sample diversity in over 5500 psycholinguistic studies published over two decades. Moreover, we consider several hitherto unexplored issues regarding diversity in (psycho)linguistics, including the impact of sample biases on knowledge uptake and the implementation of diversification strategies often proposed in the literature. We identify marked overrepresentations in the data - of English, North America, and tertiary education students - and provide new evidence of their consequences, where papers on more commonly studied languages and locations tend to be cited more. We also demonstrate that absolute diversity has increased over time, albeit insufficiently to disrupt the linguistic and geographic concentrations observed. We find that representation of Global South researchers and contexts has grown, but this growth is centered in a handful of countries (China, Israel), and Africa and Southeast Asia remain severely underrepresented. Regarding the implementation of diversification strategies, we show that online data collection has yet to contribute much to diversification, while cross-national collaboration is effective in this respect. Finally, we challenge prevalent conceptions of diversification in which "exotic" languages spoken in remote locations assume a central role by highlighting the neglected linguistic diversity of the major hubs of psycholinguistic knowledge production.

Feature refinement and attention enhancement for click-through rate prediction

Abstract Click-through rate (CTR) prediction has become a crucial task in online advertising and other fields. Many researchers focus on improving CTR prediction models by exploring feature interactions. One popular model, Deep Factorization Machine (DeepFM), addresses both high-order and low-order feature interactions, but it overlooks the variability of feature representation in different contexts and lacks a comprehensive explanation of high-order feature interactions. In this paper, we propose a CTR prediction model called DeepFM-GA, which is based on improved feature refinement generation and attention enhancement representation. Firstly, we incorporate an attention convolutional generation module into $\text{DeepFM}_{\text{FRNet}}$, which enriches the feature space by generating complementary features through convolutional neural networks while maintaining context-aware feature representation. Secondly, we utilize a multi-head self-attention layer for feature-enhanced representation, enhancing the model’s ability to select important features. Finally, experiments are conducted on four real-world datasets, and the results show that DeepFM-GA has a better performance compared to other mainstream CTR models.

Navigating ethical dimensions in algorithmic radiology: A call for action to ensure representation of low-resource contexts

Artificial intelligence (AI) has revolutionised medicine, particularly radiology, transforming our ability to interpret complex imaging data. While traditional methods rely on subjective visual assessments, AI excels at recognising intricate patterns and providing quantitative and automated evaluations. In this commentary, I delve into the various ethical considerations in algorithmic radiology, beyond the conventional concerns. Focusing on utilitarianism, patient understanding, virtue ethics, and social contract theory, the paper contributes to a comprehensive understanding of the ethical landscape surrounding AI technologies. The challenges in the use of algorithmic AI in radiology underscore the significance of the ethics of care, responsiveness to context, and the role of human emotion, whether pertaining to the practitioner, the patient, or both. The social contract theory guides the responsibilities of healthcare professionals, urging action to address biases in AI algorithms and ensuring equitable representation of various ethnic and racial populations. Diversity in data must be prioritised to avoid disparities in administering healthcare and uphold patient rights in the adoption of AI. In terms of virtue ethics, professionalism and responsibility are crucial for radiologists adopting AI. Also, an absence of explicit guidelines on the use of AI in healthcare poses challenges, necessitating further discourse. Finally, a utilitarian perspective on public health mandates a fair distribution of imaging technologies to address prevalent health issues in a given population. In conclusion, this paper advocates for an ethical approach to AI integration, which aligns technology with human values and wellbeing, as we shape the future of healthcare.

Japanese Short Answer Grading for Japanese Language Learners Using the Contextual Representation of BERT

Japanese Short Answer Grading for Japanese Language Learners Using the Contextual Representation of BERT

Memory positional encoding for image captioning

Transformer-based architectures represent the state-of-the-art in image captioning. Due to its natural parallel internal structure, it cannot be aware of the order of inputting tokens, so the positional encoding becomes an indispensable component of Transformer-based models. However, most of the existing absolute positional encodings (APE) have certain limitations for image captioning. Their spatial positional features are predefined and cannot been well generalized to other forms of data, such as visual data. Meanwhile, each positional features are decoupled from each other and lack internal correlation, therefore which affects the accuracy of spatial position context representation of visual or text semantic to a certain extent. Therefore, we propose a memory positional encoding (MPE), which has generalization ability that can be applied to both the visual encoder and the sequence decoder of the image captioning models. In MPE, each positional feature is recursively generated by the learnable network with memory function, making the current generated positional features effectively inherit the genetic information of the previous n positions. In addition, existing positional encodings provide positional features with fixed value and scale, that means, they provide the same positional encoding for different inputs, which is unreasonable. Thus, to address the previous issues of scale and value of current positional encoding methods in practical applications, we further explore dynamic memory positional encoding (DMPE) based on MPE. DMPE dynamically adjusts and generates positional features based on different input to provide them with unique positional representation. Extensive experiments on the MSCOCO validate the effectiveness of MPE and DMPE.

Fringe Texture Driven Droplet Measurement End-to-End Network Based on Physics Aberrations Restoration of Coherence Scanning Interferometry.

Accurate and efficient measurement of deposited droplets' volume is vital to achieve zero-defect manufacturing in inkjet printed organic light-emitting diode (OLED), but it remains a challenge due to droplets' featurelessness. In our work, coherence scanning interferometry (CSI) is utilized to measure the volume. However, the CSI redundant sampling and image degradation led by the sample's transparency decrease the efficiency and accuracy. Based on the prior degradation and strong representation for context, a novel method, volume measurement via fringe distribution module (VMFD), is proposed to directly measure the volume by single interferogram without redundant sampling. Firstly, the 3D point spread function (PSF) for CSI imaging is modeling to relate the degradation and image. Secondly, the Zernike to PSF (ZTP) module is proposed to efficiently compute the aberrations to PSF. Then, a physics aberration restoration network (PARN) is designed to remove the degradation via the channel Transformer and U-net architecture. The long term context is learned by PARN and beneficial to restoration. The restored fringes are used to measure the droplet's volume by constrained regression network (CRN) module. Finally, the performances on public datasets and the volume measurement experiments show the promising deblurring, measurement precision and efficiency.

The Anatomy of Context.

For most of my career, I focused on understanding how and where spatial context, the place where things happen, is represented in the brain. My interest in this began in the early 1990's, during my postdoctoral training with David Amaral, when we defined the rodent homolog of the primate parahippocampal cortex, a region implicated in processing spatial and contextual information. We parceled out the caudal portion of the rat perirhinal cortex (PER) and called it the postrhinal cortex (POR). In my own lab at Brown University, I continued to study the anatomy of the PER, POR, and entorhinal cortices. I also began to characterize and differentiate the functions of these regions, particularly the newly defined POR and the redefined PER. Our electrophysiological and behavioral evidence supports a view of POR function that aligns with our anatomical evidence. Briefly, the POR integrates object and feature information from the PER with spatial information from the retrosplenial, posterior parietal, and secondary visual cortices and the pulvinar and uses this information to represent specific environmental contexts, including the spatial arrangement of objects and features within each context. In addition to maintaining a representation of the current context, the POR plays an attentional role by continually monitoring the context for changes and updating the context representation when changes occur. This context representation is accessible to other regions for cognitive processes, including binding life events with context to form episodic memories, guiding context-relevant behavior, and recognizing objects within scenes and contexts.

Multi-Agent Hierarchical Graph Attention Actor-Critic Reinforcement Learning.

Multi-agent systems often face challenges such as elevated communication demands, intricate interactions, and difficulties in transferability. To address the issues of complex information interaction and model scalability, we propose an innovative hierarchical graph attention actor-critic reinforcement learning method. This method naturally models the interactions within a multi-agent system as a graph, employing hierarchical graph attention to capture the complex cooperative and competitive relationships among agents, thereby enhancing their adaptability to dynamic environments. Specifically, graph neural networks encode agent observations as single feature-embedding vectors, maintaining a constant dimensionality irrespective of the number of agents, which improves model scalability. Through the "inter-agent" and "inter-group" attention layers, the embedding vector of each agent is updated into an information-condensed and contextualized state representation, which extracts state-dependent relationships between agents and model interactions at both individual and group levels. We conducted experiments across several multi-agent tasks to assess our proposed method's effectiveness, stability, and scalability. Furthermore, to enhance the applicability of our method in large-scale tasks, we tested and validated its performance within a curriculum learning training framework, thereby enhancing its transferability.

Prediction and Detection of Scam Threats on Digital Platforms for Indonesian Users Using Machine Learning Models

Scam threats on digital platforms continue to rise alongside the rapid adoption of technology in Indonesia. The unique characteristics of Indonesian digital users, such as low digital literacy and high social media usage, make them particularly vulnerable to various forms of scams, including phishing, impersonation, and emotional manipulation. This study aims to develop a machine learning-based model for predicting and detecting scams by identifying threat patterns within a local context. The methodology involves collecting a survey-based dataset from Indonesian digital users, capturing language patterns and user interaction behaviors. The dataset was processed through text-cleaning techniques, tokenization, normalization, and representation using TF-IDF and Word Embeddings. The machine learning models employed in this study are Random Forest and Support Vector Machine (SVM), evaluated using accuracy, precision, recall, and F1-score metrics. Hyperparameter tuning was conducted to optimize model performance, while k-fold cross-validation was utilized to minimize the risk of overfitting. The results indicate that the Random Forest model achieved the best performance, with an accuracy of 92.5%, precision of 90.7%, recall of 94.1%, and F1-score of 92.4%. The use of local datasets improved detection accuracy by 7.8% compared to global datasets, highlighting the critical importance of contextual representation in identifying scam patterns specific to Indonesia. The model was also effective in recognizing unique threat patterns, such as the use of informal language and manipulative phrases in scam messages. This study makes a significant contribution to the field of digital security by providing an effective machine learning-based approach to detecting scam threats in Indonesia. Moreover, the findings underscore the importance of developing local datasets and educating users as part of a holistic solution to enhance digital security. These insights emphasize the necessity of incorporating cultural and contextual factors into technology-driven approaches for combating scams in developing countries like Indonesia

Distributed Representations for Cognitive Control in Frontal Medial Cortex.

In natural and artificial neural networks, modularity and distributed structure afford complementary but competing benefits. The former allows for hierarchical representations that can flexibly recombine modules to address novel problems, whereas the latter can benefit from less constrained training, potentially uncovering fruitful statistical regularities. Here, we investigate these competing demands in the context of human sequential behavior. First, we explore this setting by comparing the properties of several recurrent neural network models. We find that explicit hierarchical structure by itself fails to provide a critical performance advantage when compared with a "flat" model that does not incorporate hierarchical structure. However, hierarchy appears to facilitate cognitive control processes that support nonroutine behaviors and behaviors that are carried out under computational stress. Second, we compare these models against fMRI data using representational similarity analysis. We find that a model that incorporates so-called wiring costs in the cost function, which produces a hierarchically organized gradient of representational structure across the hidden layer of the neural network, best accounts for fMRI data collected from human participants in a previous study [Holroyd, C. B., Ribas-Fernandes, J. J. F., Shahnazian, D., Silvetti, M., & Verguts, T., Human midcingulate cortex encodes distributed representations of task progress. Proceedings of the National Academy of Sciences, U.S.A., 115, 6398-6403, 2018]. The results reveal that the ACC encodes distributed representations of sequential task context along a rostro-caudal gradient of abstraction: Rostral ACC encodes relatively abstract and temporally extended patterns of activity compared with those encoded by caudal ACC. These results provide insight into the role of ACC in motivation and cognitive control.

Health and ethnic minorities in the Media: An analysis of the coverage of Indigenous peoples' health before and during the COVID-19 pandemic in Peru

This essay about the media coverage of Indigenous peoples' health in Peru reveals a consistent lack of depth and nuance. Pre-pandemic, domestic outlets echoed governmental perspectives without critical analysis of the indigenous healthcare conditions; while international media, though acknowledging discrimination and primarily focused on environmental issues, did not make explicit connections between both topics and the limited access to health services in these communities. This trend continued during the pandemic, with domestic coverage remaining superficial and international media largely ignoring the pandemic's impact on indigenous communities. It reveals a persistent racism within the press, so it is possible to affirm the historical power imbalances stemming from colonialism continue shaping news framing, agenda-setting and the determination of news value both domestically and internationally, being that media representations in a post-colonial context reinforce stereotypes of formerly colonized people, whose voices and issues are considered newsworthy only when they if fit certain narratives.

Enhancing diabetic retinopathy and macular edema detection through multi scale feature fusion using deep learning model.

This work tackles the growing problem of early identification of diabetic retinopathy and diabetic macular edema. The deep neural network design utilizes multi-scale feature fusion to improve automated diagnostic accuracy. Methods This approach uses convolutional neural networks (CNN) and is designed to combine higher-level semantic inputs with low-level textural characteristics. The contextual and localized abstract representations that complement each other are combined via a unique fusion technique. Use the MESSIDOR dataset, which comprisesretinal images labeled with pathological annotations, for model training and validation toensure robust algorithm development. The suggested model shows a 98% general precision and good performance in diabetic retinopathy. This model achieves an impressive nearly 100% exactness for diabetic macular edema, with particularly high accuracy (0.99). Consistent performance increases the likelihood that the vision will be upheld through public screening and extensive clinical integration.

Novel approach for Arabic fake news classification using embedding from large language features with CNN-LSTM ensemble model and explainable AI

The widespread fake news challenges the management of low-quality information, making effective detection strategies necessary. This study addresses this critical issue by advancing fake news detection in Arabic and overcoming limitations in existing approaches. Deep learning models, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), EfficientNetB4, Inception, Xception, ResNet, ConvLSTM and a novel voting ensemble framework combining CNN and LSTM are employed for text classification. The proposed framework integrates the ELMO word embedding technique having contextual representation capabilities, which is compared with GloVe, BERT, FastText and FastText subwords. Comprehensive experiments demonstrate that the proposed voting ensemble, combined with ELMo word embeddings, consistently outperforms previous approaches. It achieves an accuracy of 98.42%, precision of 98.54%, recall of 99.5%, and an F1 score of 98.93%, offering an efficient and highly effective solution for text classification tasks.The proposed framework benchmark against state-of-the-art transformer architectures, including BERT and RoBERTa, demonstrates competitive performance with significantly reduced inference time and enhanced interpretability accompanied by a 5-fold cross-validation technique. Furthermore, this research utilizes the LIME XAI technique to provide deeper insights into the contribution of each feature in predicting a specific target class. These findings show the proposed framework’s effectiveness in dealing with the issues of detecting false news, particularly in Arabic text. By generating higher performance metrics and displaying comparable results, this work opens the way for more reliable and interpretable text classification solutions.

The thalamus encodes and updates context representations during hierarchical cognitive control.

Cognitive flexibility relies on hierarchically structured task representations that organize task contexts, relevant environmental features, and subordinate decisions. Despite ongoing interest in the human thalamus, its role in cognitive control has been understudied. This study explored thalamic representation and thalamocortical interactions that contribute to hierarchical cognitive control in humans. We found that several thalamic nuclei, including the anterior, mediodorsal, ventrolateral, and pulvinar nuclei, exhibited stronger evoked responses when subjects switch between task contexts. Decoding analysis revealed that thalamic activity encodes task contexts within the hierarchical task representations. To determine how thalamocortical interactions contribute to task representations, we developed a thalamocortical functional interaction model to predict task-related cortical representation. This data-driven model outperformed comparison models, particularly in predicting activity patterns in cortical regions that encode context representations. Collectively, our findings highlight the significant contribution of thalamic activity and thalamocortical interactions for contextually guided hierarchical cognitive control.