Search Results (4,738)

To enhance the performance of the Social Network Search (SNS) algorithm in solving complex numerical optimization problems, this paper proposes a Multi-strategy Enhanced Social Network Search (MESNS) algorithm. The original SNS simulates human social behaviors through four decision-making emotions—imitation, conversation, disputation, and innovation—to perform population-based search. However, its uniform emotion selection mechanism and purely random interaction strategy may reduce convergence efficiency and weaken exploitation capability, particularly in the later stages of optimization. To overcome these limitations, MESNS incorporates three improvement strategies. First, an adaptive decision-making emotion selection mechanism is developed to dynamically adjust the probabilities of exploration and exploitation behaviors according to the iteration progress, thereby promoting a more symmetric and coordinated search transition over time. Second, an elite-guided communication strategy is introduced to enhance information propagation by integrating high-quality individuals into the interaction process, which improves convergence while maintaining population diversity. Third, a dynamic interaction radius adjustment mechanism is designed to adaptively regulate the search step size, achieving a better balance and dynamic symmetry between global exploration and local refinement. Extensive experiments are conducted on the IEEE CEC2014, CEC2017, and CEC2022 benchmark suites under multiple dimensional settings. The results demonstrate that MESNS achieves superior optimization accuracy, faster convergence speed, and improved solution stability compared with several state-of-the-art metaheuristic algorithms. Furthermore, the proposed algorithm is successfully applied to the three-dimensional wireless sensor network deployment optimization problem, where it produces a more uniformly distributed and spatially balanced sensor layout, reduces coverage holes and redundant overlaps, and thus exhibits desirable symmetry in deployment structure and sensing coverage. These findings indicate that MESNS is an effective and competitive optimization framework for complex global optimization tasks with both theoretical significance and practical value from the perspective of symmetry. Full article

Model-Agnostic Meta-Learning (MAML) and Prototypical Networks (ProtoNet) establish the foundational paradigms for few-shot classification. However, MAML suffers from optimization instability caused by reconstructing classification boundaries for every new task. Conversely, ProtoNet lacks the internal mathematical capacity necessary for task-specific parameter adaptation under domain shifts. To reconcile these structural limitations, we introduce Metric-based Model-Agnostic Meta-Learning (M²AML). By completely excising the parameterized classification layer from the episodic adaptation sequence, our framework replaces traditional inner-loop classification with a dynamic self-exclusive geometric similarity metric. Substituting functional mappings with spatial distance optimizations efficiently resolves evaluation conflicts, thereby establishing perfectly synchronized inner and outer learning rates alongside substantially accelerated adaptation steps. Extensive experiments across mini-ImageNet, tiered-ImageNet, and CIFAR-FS validate our approach against a comprehensive array of established algorithms. To ensure strictly fair comparative evaluations, we meticulously reproduce the MAML, ProtoNet, and Proto-MAML baselines. Empirical results demonstrate that M²AML achieves state-of-the-art performance across most evaluation settings, delivering absolute accuracy improvements ranging from 0.1% to 2.1% over existing leading models. Full article

Recent years have witnessed significant progress in deep learning-based shadow removal. However, most prior methods operate primarily in the spatial domain or rely on coarse frequency cues, while the informative role of amplitude components in the frequency domain remains largely unexplored. The amplitude spectrum encodes spectral energy that reflects global illumination and fine texture that strongly influence shadow appearance. Motivated by this observation, we propose AmpFormer, a U-shaped transformer architecture that explicitly models amplitude information for robust shadow correction. Central to AmpFormer is a lightweight SFR module inserted at each encoder–decoder stage: SFR extracts multi-scale amplitude cues from compact spectral representations, learns per-channel adaptive gains and subtle phase adjustments, and injects the recalibrated frequency features into the spatial stream. To further encourage amplitude-aware restoration, we introduce an amplitude loss that explicitly regularizes spectral energy with emphasis on global illumination consistency. Extensive experiments on standard benchmarks demonstrate that AmpFormer achieves state-of-the-art restoration quality while offering a favorable computational-efficiency-accuracy trade-off, validating the practical benefit of amplitude-aware frequency modeling for shadow removal. Full article

To address the bottlenecks of accuracy in head pose estimation caused by occlusion and rotational representation ambiguities, we propose Deep6DHead, a 6-degree-of-freedom (6DoF) head pose estimation method based on deep feature enhancement. This method innovatively integrates RGB and depth information to construct a four-channel input and achieves feature fusion of RGB-D through a dual-branch network. First, a Squeeze-and-Excitation (SE) module adaptively weights the depth geometric features of key anatomical regions to achieve channel recalibration. Second, based on the 6DoF rotation representation framework, we introduce an anatomical constraint loss using the nasal bridge normal. This constraint corrects rotation deviations caused by noise by enforcing consistency in local geometric orientation. Finally, the model outputs the rotation matrix end-to-end for final pose estimation. Experiments on the 300W-LP, BIWI, and AFLW2000 datasets demonstrate that our method significantly improves robustness and accuracy, particularly under extreme head poses. Notably, it achieves state-of-the-art performance on the roll axis (lowest error: 2.05) and a competitive overall MAE of 3.45, providing an effective solution for head pose estimation in complex real-world scenarios including extreme viewing angles. Full article

The widespread deployment of unmanned aerial vehicles (UAVs) in civil and commercial airspace has raised significant safety concerns, driving the demand for reliable and real-time Anti-UAV visual detection systems. However, existing deep learning-based detectors face substantial challenges in complex low-altitude environments, including drastic scale variations, severe background clutter, and weak feature representation of small UAV targets. Moreover, handcrafted Transformer-based architectures often lack adaptability across diverse scenarios and struggle to balance detection accuracy with computational efficiency. To address these limitations, this paper proposes AutoUAVFormer, a super-resolution guided neural architecture search framework for Anti-UAV detection. In contrast to conventional manually designed approaches, AutoUAVFormer leverages joint optimization of a Transformer-based detection objective and a super-resolution reconstruction objective to automatically identify a task-specific optimal network architecture for detecting UAV targets. Specifically, a unified search space is formulated by jointly embedding Transformer hyperparameters and Feature Pyramid Network (FPN) structures, facilitating end-to-end co-optimization of multi-scale feature fusion and global context modeling. To efficiently locate architectures that balance accuracy and computational cost, a three-stage pipeline, combining supernetwork training with evolutionary search, is employed. Additionally, we design a super-resolution auxiliary branch that operates only during training to enhance the model’s ability to learn fine-grained textures and sharpen edge representations of small targets, without introducing any inference overhead. Extensive experiments on three challenging Anti-UAV detection benchmarks, namely DetFly, DUT Anti-UAV, and UAV Swarm, confirm the superiority of AutoUAVFormer over current state-of-the-art methods, with mAP@0.5 scores reaching 98.6%, 95.5%, and 89.9% on the respective datasets while sustaining real-time inference speed. These results demonstrate that AutoUAVFormer achieves strong generalization and maintains robust Anti-UAV detection performance under challenging low-altitude conditions. Full article

Dissemination and conservation of cultural heritage have been challenged by continued accessibility in museums, where traditional information delivery systems are at times ineffective in terms if interaction with visitors. The current paper investigates RumiArt IA, a mobile application, to identify cultural objects in real-time, remaining fully in the scope of this line of research without relying on internet connectivity. The system, which is developed based on the Rumiñahui Museum and Cultural Center, Ecuador, uses transfer learning in the MobileNetV2 architecture with INT8 post-training quantization to identify 21 cultural artifacts spread across six thematic rooms. The experiment involved building a dataset of 36,000 images under diverse lighting conditions, viewing angles, and distances; furthermore, artificial transformations were explicitly crafted to simulate real museum conditions such as glass reflections and non-frontal capture angles. Quantization was used to reduce each model to 775 KB as compared with the 2.4 MB, with accuracy loss not reaching more than 0.5 percent (DKL < 0.05). Assessment of 9450 validation images yielded a general accuracy of 92.2%, with an inference time of 63 ms on current devices with a high throughput and 215 ms on mid-range hardware from 2020. Practical validation involving 50 visitors of the museum showed a success rate of 93.7%, with average user satisfaction at 8.5/10 and 87%, indicating they would recommend the application. An in-depth error study of the most difficult room (88.3% accuracy) indicated that 47% of the errors were due to the angles of the camera, which blocked out distinguishing features, and 22% were caused by display case reflections and the shadows of the visitors. These results indicate that end-to-end machine learning can provide consistent cultural heritage recognition in resource-constrained settings but its efficiency is susceptible to physical capture factors that cannot be resolved by data augmentation. Offline mode and low memory footprint (less than 90 MB when loaded on six models) of the system are especially relevant to application in situations where there is no guarantee of cloud connectivity. Full article

Symmetric matrix factorization (SMF) plays an important role in clustering and representation learning. Nevertheless, most existing SMF-based approaches are formulated as non-convex optimization problems, which often leads to unstable convergence and high computational costs. In this paper, we develop a fast unconstrained convex symmetric matrix factorization framework, termed FUCSMF, for semi-supervised learning. By incorporating label information into the symmetric factorization formulation, the proposed model is transformed into a convex objective, which guarantees global optimality and enables efficient optimization using standard unconstrained solvers. To further improve scalability, a bipartite graph structure is introduced into SMF from a hypergraph-inspired perspective, significantly reducing the computational burden. The resulting computational complexity is reduced to $O\left(nmd\right)$, which is substantially lower than the $O(nmd+m^{2}n+m^3)$ complexity required by existing bipartite graph-based methods, where n, m, and d denote the numbers of samples, anchor points, and feature dimensions, respectively. In addition, we propose a correntropy-based graph construction strategy to alleviate the sensitivity of conventional adaptive neighbor bipartite graph methods. Extensive experiments on six benchmark datasets, involving comparisons with eleven state-of-the-art methods, demonstrate that FUCSMF achieves superior clustering performance while requiring significantly less computational time. Empirical results further show that the proposed method converges rapidly, typically within ten iterations. Full article

X-ray free-electron lasers (XFELs) have revolutionized structural biology by enabling “diffraction-before-destruction” and capturing the ultrafast dynamics of life. However, the intrinsic sparsity and noise of XFEL diffraction snapshots, often complicated by multi-lattice overlaps, create a formidable computational bottleneck that limits data utilization and structural fidelity. Here, we present MCDPS-SFX, a robust indexing framework based on a reference-based, whole-pattern matching principle integrated with parallelized iterative refinement. By exhaustively sampling orientation space and progressively rejecting outliers, MCDPS-SFX significantly outperforms legacy algorithms—more than doubling crystal yields in heterogeneous datasets (e.g., 21,807 vs. 8792 for MOSFLM)—and achieves highly competitive yields comparable to state-of-the-art indexers, such as extracting over 90,000 lattices in the lysozyme benchmark. We demonstrate its efficacy on standard benchmarks and technically demanding G-protein-coupled receptor (GPCR) systems, including the rhodopsin–arrestin complex and the glucagon receptor. MCDPS-SFX consistently produces high-quality data statistics, enabling the high-resolution visualization of functionally critical, flexible regions such as phosphorylated receptor tails. Our results provide a powerful tool for enhancing the scientific output of XFEL experiments, offering a robust alternative for maximizing information recovery from weakly diffracting or overlapping crystalline samples. Full article

Hyperspectral unmixing aims to estimate endmember spectra and their corresponding abundance fractions at the subpixel scale, which is a critical preprocessing step for quantitative analysis of hyperspectral remote sensing imagery. While deep learning-based methods have achieved remarkable progress, three fundamental challenges remain: (i) reliance on a single shared spatial prior that cannot decouple the heterogeneous spatial patterns of different land covers; (ii) the lack of synergy in jointly optimizing endmember extraction and abundance estimation; (iii) the poor robustness of unsupervised training to complex mixtures, noise, and class imbalance. To address these issues, we propose a novel unsupervised unmixing framework that integrates adaptive orthogonal multi-faceted graph representation with curriculum learning. Specifically, we design an Adaptive Orthogonal Multi-Faceted Graph Generator (AOMFG) to learn a set of independent orthogonal graph structures, achieving spatially informed decoupling of land cover patterns. Then, a dual-branch collaborative optimization network is constructed: a Graph Convolutional Network (GCN) branch that incorporates the learned spatial topological priors for abundance estimation, and a 1D Convolutional Neural Network (1DCNN) branch that employs a query-attention mechanism to adaptively aggregate pure spectral features for endmember extraction. Finally, we introduce a three-stage curriculum learning strategy that progressively fine-tunes the model, which significantly enhances its performance. Extensive experiments on three widely used real-world benchmark datasets demonstrate that our proposed framework consistently outperforms state-of-the-art methods in both endmember extraction and abundance estimation accuracy. Comprehensive ablation studies, parameter sensitivity analysis, and noise robustness tests further validate the effectiveness of each core component. Full article

The use of long-distance transoceanic cables equipped with high-loss loopbacks enables distributed sensing with a resolution determined by amplifier spacing, typically in the order of 50–100 km. Microwave-frequency fiber interferometry is a promising trans-mission technique for investigating long links supported by periodic optical amplification. In this paper, we propose a variant of this technique that ensures compatibility with links containing high-loss loopbacks, thereby transforming the integrated sensing approach into a distributed one. We highlight the critical modifications required to overcome challenges associated with the detection of multiple return signals, and we conduct a proof-of-principle experiment using a two-loop configuration. We demonstrate the concept by detecting and localizing low-frequency (<10 Hz) events—whether human-generated or induced by fiber stretchers—with span-level resolution. This validates the potential of the modified microwave-frequency interferometry approach for transoceanic cable monitoring in scenarios where high-loss loopbacks are present. We also present a theoretical analysis that evaluates the limits of the technique across different frequency ranges, in comparison with optical interferometry methods based on high-spectral-purity fiber lasers. The analysis shows that for long amplifier spacings (~100 km), micro-wave-frequency fiber interferometry exhibits a signal-to-noise ratio advantage at sub-Hz frequencies (<0.1 Hz) compared to state-of-the-art optical interferometers. Full article

Christian philosophers, theologians, and artists regularly claim that experiences of beauty in art can function (i) as a road to God and (ii) as an encounter with God. These claims are well motivated by various Biblical texts and sophisticated theistic accounts of aesthetic perception. What is often lacking, however, is empirical support for key premises in arguments supporting these common claims. As a result, the connection between beauty, art, and God remains tentative and subject to defeat by empirically grounded naturalistic accounts of aesthetic perception. In this essay, we will identify the key empirical premises supporting these common claims and suggest the application of the emerging field, experimental theological aesthetics, for empirically testing such premises. If successful, the resultant experimentally based approach to philosophical and theological aesthetics suggests new ways of advancing long-standing debates typically carried out along theoretical or a priori lines with little or no appeal to empirical concerns. Full article

The rapid proliferation of unmanned aerial vehicles (UAVs) has amplified the need for robust and efficient object detection in diverse aerial environments. However, detecting small objects under complex conditions (e.g., low illumination, cluttered backgrounds, and thermal–visual discrepancies) remains challenging. While many existing detectors emphasize real-time inference, they often rely on weak or late fusion strategies, resulting in suboptimal utilization of complementary multi-modal cues. To address this limitation, we propose DGE-YOLO, an enhanced YOLO-based framework for effective infrared–visible (IR–RGB) multi-modal fusion in UAV object detection. DGE-YOLO adopts a dual-branch architecture for modality-specific feature extraction, preserving modality-aware representations before fusion. To strengthen cross-scale semantics, we introduce an Efficient Multi-scale Attention (EMA) module that improves feature discrimination across spatial resolutions. Furthermore, we replace the conventional neck with a Gather-and-Distribute module to reduce information loss during feature aggregation and improve multi-scale feature propagation. Extensive experiments on the DroneVehicle dataset demonstrate that DGE-YOLO consistently outperforms state-of-the-art baselines, confirming its effectiveness and practicality as an applied multi-modal detection solution for UAV scenarios. Full article

Image hashing enables efficient large-scale image retrieval by encoding high-dimensional visual data into compact binary representations. However, existing deep hashing methods typically learn fixed-length hash codes in a fully supervised manner, often generating redundant bits that limit discriminative capability and increase storage overhead. In this paper, we propose a deep reinforcement learning-based adaptive bit selection framework for compact image hashing. We formulate hash refinement as a Markov Decision Process (MDP) and employ a Proximal Policy Optimization (PPO) agent to selectively retain the most informative hash bits while discarding redundant ones, directly optimizing retrieval performance through mean Average Precision (mAP). The proposed approach integrates CNN-based hash extraction with reinforcement-driven adaptive regeneration, producing compact yet highly discriminative binary codes. Extensive experiments on standard image retrieval benchmarks demonstrate consistent improvements over state-of-the-art deep hashing methods in terms of retrieval accuracy and efficiency, highlighting the effectiveness of reinforcement learning for adaptive representation learning in intelligent large-scale retrieval systems. Full article

With the advancement of 3D digital dentistry, accurate 3D tooth segmentation has become increasingly important in orthodontics and computer-aided diagnosis. However, existing supervised approaches heavily rely on exhaustive face-wise annotations and often exhibit limited generalization across complex clinical meshes. Although self-supervised learning offers a promising alternative to alleviate annotation costs, current paradigms remain challenged by sensitivity to data augmentations, suboptimal representation learning in pure masking schemes, and the complex structural characteristics of dental geometry. To address these limitations, we propose Dental-CMAE, a graph-enhanced hierarchical Contrastive masked AutoEncoder framework tailored for 3D tooth segmentation. The framework incorporates a dual-branch masking strategy that leverages graph-based structural priors to generate distinct corrupted views while preserving intrinsic mesh topology, thereby facilitating robust reconstruction. This is integrated with a feature-level contrastive objective designed to enforce semantic consistency between co-masked regions, which enhances representation discriminability without the requirement for negative sample queues. Additionally, the architecture utilizes a hierarchical multi-scale attention mechanism that partitions feature channels into parallel streams, enabling the simultaneous capture of fine-grained morphological variations and the overarching global dental arch context. Extensive experiments demonstrate that our Dental-CMAE consistently outperforms state-of-the-art fully supervised and self-supervised methods across multiple evaluation metrics. Specifically, our framework achieves an Overall Accuracy (OA) of 95.57%, a mean Intersection-over-Union (mIoU) of 88.14%, and a mean Accuracy (mAcc) of 90.85%. Supported by these quantitative findings, our method validates its effectiveness for robust 3D tooth segmentation, highlighting its strong potential to alleviate annotation bottlenecks and improve the reliability of automated 3D digital dental workflows. Full article

The collaboration of ground vehicles (GVs) and drones offers a powerful approach for enhancing drone capabilities. Current research focuses on drone-only or single-type target reconnaissance, failing to adequately account for practical scenarios. This paper introduces a GV–drone collaboration routing problem with multi-type target reconnaissance (GVD-MTR), which explicitly integrates GV–drone collaboration with simultaneous reconnoitering of point, line, and area targets. To address this problem, we propose a knowledge-driven two-stage hybrid algorithm (KDHA). In the first stage, K-means clustering combined with heuristic operators is applied to generate and refine routes for the GV. In the second stage, an improved Adaptive Large Neighborhood Search (IALNS) method is implemented to produce optimized drone routes. KDHA leverages hybrid search strategies, such as a population-based initialization strategy and a multi-level acceptance strategy, to efficiently generate high-quality solutions. Regarding recognizing the impacts of different target types on the total travel distance, we incorporate the related domain knowledge to design problem-specific search operators. Extensive simulation experiments demonstrate that KDHA consistently outperforms several state-of-the-art heuristics in terms of solution quality and runtime. Sensitivity analyses further confirm the robustness of the proposed approach across a range of parameter settings and problem instances. Full article