• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    C

    CRSTRA

    EST. 1991
    165论文总数
    714引用总数

    论文量&引用量时间轴

    机构学者

    论文(165)

    年份
    起
    –
    止
    排序
    1Enhancing Facial Beauty Prediction with a Cross-Attention Vision Transformer and Attention-Guided Augmentation
    D. E. Boukhari, F. Dornaika

    Facial Beauty Prediction (FBP) is a long-standing and inherently challenging task in computer vision, primarily due to the subjective and multifaceted nature of human aesthetic judgment. Perceived facial beauty is influenced by a combination of global facial harmony, local feature attractiveness, and cultural or individual biases—factors that are often difficult to quantify or model explicitly. While deep learning has significantly advanced the field, existing approaches frequently rely on convolutional backbones that emphasize local texture details but fail to capture the subtle, holistic relationships among facial components that define aesthetic perception. To address these limitations, we introduce TransFBP, a novel Vision Transformer (ViT)-based framework specifically designed for interpretable and human-aligned facial beauty assessment. The proposed model incorporates two major innovations. First, we develop a Cross-Attention Head that acts as a dynamic filter, enabling the network to automatically focus on the most visually meaningful facial areas—such as the eyes, lips, and overall symmetry—while suppressing irrelevant background information. This design enables the model to focus adaptively on semantically meaningful areas—such as the eyes, lips, and overall facial symmetry—thereby offering interpretable insights into what drives the aesthetic predictions. Second, to mitigate overfitting and enhance generalization, we propose Attention-Guided TransMix, a two-stage semantic data augmentation strategy. In the first stage, the method generates challenging hybrid samples by conditionally mixing images from opposite ends of the beauty score distribution, encouraging the model to learn discriminative features across a wide aesthetic spectrum. In the second stage, the model’s own attention maps are leveraged to generate a semantically grounded supervisory score for each mixed image, ensuring that the augmented samples remain perceptually meaningful and score-consistent. We comprehensively evaluate TransFBP on the FBP5500 dataset, where our method achieves a state-of-the-art Pearson Correlation Coefficient (PCC) of 0.9291, surpassing existing approaches. The strong empirical results validate the effectiveness of our cross-attention mechanism and attention-guided augmentation strategy. Moreover, the interpretability of our attention maps provides valuable transparency into the model’s decision process, paving the way for more explainable, reliable, and ethically aligned AI systems in aesthetic perception tasks. The code will be available at https://github.com/DjameleddineBoukhari/transFBP We introduced TransFBP, a novel Transformer-based framework that advances both the performance and interpretability of facial beauty prediction. The proposed approach is characterized by two key innovations: a Cross-Attention Head, which enables the model to dynamically integrate the most salient and contextually relevant facial features, and an Attention-Guided TransMix augmentation strategy, which enhances regularization by generating semantically consistent and challenging training samples.

    2026Cognitive Computation(2026)引用:7
    引用
    AI阅读
    加入学术空间
    2Prioritizing Flood Vulnerability Hotspots: an Integrated AHP and TOPSIS Framework, Case Study of El Bayadh City, Western Algeria
    Meriem Boultif,Mohammed Amin Hafnaoui

    Algeria ranks among the countries most frequently affected by floods on an annual basis, particularly in urban and peri-urban areas. The lack of data-most notably detailed maps of flood-prone zones-forces authorities to rely on limited information when planning infrastructure development and implementing disaster mitigation strategies.This study aims to model the most vulnerable areas to flooding in the city of El Bayadh, located in western Algeria, by proposing a methodology based on multicriteria analysis. Specifically, the Analytic Hierarchy Process is applied to provide a comprehensive overview of the city's flood vulnerability status, followed by the use of Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to model critical areas or hotspots. This study employs several urban factors, namely urban density, population density, land use, building quality, and building age. The results of the study indicate that 55.68 ha of land within the city are identified as critical hotspots, of which 48 ha are classified as highly vulnerable hotspots requiring immediate intervention to mitigate flood risk, this study was further reinforced through a sensitivity analysis, where the calculated AUC value reached 0.91, demonstrating the efficiency of the proposed approach in flood modeling within the study area, moreover, the convergence between Moran's I results, Hotspot Analysis, and GWR residuals provides robust evidence that flood vulnerability in the study area is not random but highly clustered. These spatial clusters represent systemic weaknesses and should be prioritized for targeted local-scale flood mitigation strategies.

    2026JOURNAL OF AFRICAN EARTH SCIENCES(2026)
    引用
    AI阅读
    加入学术空间
    3H-ARN: A Holo-Attentive Relational Network for Holistic Facial Beauty Prediction Via Distribution Learning
    D. Eddine Boukhari, F. Dornaika, J. Charafeddine

    Facial Beauty Prediction (FBP) remains a significant challenge in computer vision, primarily due to the inherent subjectivity of human perception and the difficulty in modeling the holistic harmony of facial features. Existing deep learning models, typically based on Convolutional Neural Networks (CNNs), often regress a deterministic score and struggle to surpass a performance plateau. In this work, we propose the Holo-Attentive Relational Network (H-ARN), a novel architecture designed to overcome these fundamental limitations. H-ARN makes two primary contributions: (1) It pioneers the use of distribution learning by predicting the mean and variance of beauty scores, employing a Gaussian Negative Log-Likelihood loss to robustly model the subjectivity and ambiguity in training data. (2) It introduces a relational self-attention module atop a powerful Vision Transformer (ViT) backbone, explicitly learning the complex, long-range relationships between facial components that define aesthetic harmony. Evaluated on the challenging SCUT-FBP5500 benchmark, our proposed H-ARN achieves a new state-of-the-art Pearson Correlation of 0.9333, significantly outperforming previous methods. The code will be made publicly available upon publication https://github.com/DjameleddineBoukhari/H-ARN .

    2026International Journal of Multimedia Information Retrieval(2026)
    引用
    AI阅读
    加入学术空间
    4Melliferous Flora in Arid Regions of Algeria (case of Biksra)
    Khalila Bengouga, Souad Taharchaouche, Farida Bettiche, Ouahiba Mizab, Zine Eddine Benguega

    Melliferous flora diversity of the arid region Biskra located at South East Algeria is revealed in the present study. Through visual inspection, information collected from local guides of different prospected sites when we collected samples. Then a list of plant species valuable for honey bees was established. The list consisted of 122 species distributed in 102 genera and 43 families though the most represented were in decreasing order Asteraceae (22 species), Fabaceae (14 species), Apiaceae (8 species), Brassicaceae and Lamiaceae (with 7 species for each family), Boraginaceae (4 species). These families alone account for a half (51.23%) of all taxa identified. However, Anacardiaceae, Resedaceae, Rosaceae and Solonaceae were represented by 3 species for each family, Amaranthaceae, Apocynaceae, Asphodelaceae, Cistaceae, Cleomaceae, Cucurbitaceae, Cuperaceae, Lythiraceae, Nitraceae, Oleaceae, Plombaginaceae, Rutaceae, Tamaricaceae and Zygophylaceae were represented by 2 species for each family. The rest of the families were represented by one species. A flowering calendar as well as apicultural value of the most common melliferous plants is given. Melliferous flora included 37.70% nectariferous and polliniferous at the same time species, 31.15 % polliniferous species, 27.86% nectariferous species, 1,64% were sources of propolis and 0.82% were sources of resin.

    2026MEDITERRANEAN BOTANY(2026)
    引用
    AI阅读
    加入学术空间
    535. Breeding with the People: Farmer-Led Strategies for Sustainable Sheep in Arid Organic Systems
    A. Atia, H. Brahim, H. Leyla, T. Boussaada
    2026Animal - Science proceedings(2026)
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 165 篇论文

    合作机构(66)

    Ider University合作论文 11
    比斯拉大学合作论文 11
    Badji Mokhtar University合作论文 10
    Batna 1 University合作论文 6
    University of Ouargla合作论文 5
    Houari Boumediene科技大学合作论文 5
    École Normale Supérieure de Bouzareah Alger合作论文 4
    拉古亚特大学合作论文 4
    Institut National de la Recherche Agronomique d'Algérie合作论文 3
    École Nationale Supérieure Agronomique合作论文 3

    机构统计