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.
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.
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 .
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.