Search Results (3,154)

Worldwide visual geo-localization aims to predict the geographic coordinates of an image capture location from visual content alone, posing unique challenges due to the vast scale of the Earth’s surface and pervasive visual ambiguity across distant regions. Existing approaches face distinct limitations as follows: retrieval-based methods demand massive geo-tagged databases and scale poorly; alignment-based models lack interpretability and are vulnerable to visually similar scenes; and large vision-language models (LVLMs) offer semantic reasoning but suffer from hallucination. A natural solution is retrieval-augmented generation (RAG), yet we observe that directly injecting retrieved candidates as context causes severe context poisoning. To address this, we propose HybridGeo, a dual-stream late-fusion framework that decouples retrieval from reasoning. A retrieval stream applies continuous alignment with spatial–semantic clustering to produce stable regional anchors; a reasoning stream performs context-free Chain-of-Thought inference to yield an independent coordinate estimate. The two streams are fused only at the decision stage via a spatial–consistency module that triggers weighted averaging under agreement or confidence-based arbitration under conflict. Experiments on Im2GPS3k show that HybridGeo achieves 73.89% Country@750km accuracy, outperforming the retrieval baseline by 7.27% and 8.23%, and surpassing both VLM-only and RAG baselines. These results demonstrate that late fusion effectively avoids context poisoning while enabling complementary benefits from both streams. Full article

Cross-view geo-localization (CVGL) aims to match ground-level images with geo-tagged aerial imagery for precise localization, but remains challenging due to severe viewpoint discrepancies, partial correspondence, and significant domain shifts across geographic regions. While existing methods achieve high accuracy within specific datasets, their generalization ability to unseen environments is limited. In this paper, we propose GenGeo, a unified framework that integrates vision foundation model representations with a matching-aware aggregation mechanism to address these challenges. Specifically, we leverage DINOv2 to extract semantically rich and transferable features, and revisit the SALAD aggregation module in the context of CVGL. By employing a shared clustering strategy, the proposed framework projects cross-view features into a unified assignment space, enabling implicit semantic alignment across views, while the dustbin mechanism effectively filters unmatched and non-informative regions arising from partial correspondence. Extensive experiments on three large-scale benchmarks (CVUSA, CVACT, and VIGOR) demonstrate that GenGeo achieves state-of-the-art performance in cross-dataset generalization and consistently improves robustness under severe domain shifts and spatial misalignment. Notably, our method outperforms the baseline by 14.65% in Top-1 Recall on the CVUSA-to-CVACT transfer task. These results highlight the effectiveness of combining foundation model representations with matching-aware aggregation, and suggest that enforcing semantic consistency in a shared assignment space is a promising direction for generalizable cross-view geo-localization. Full article

Artificial intelligence (AI) is increasingly used to support tuberculosis (TB) screening and diagnosis, particularly through computer-aided detection (CAD) applied to chest radiography (CXR). However, the programmatic value of AI depends not only on diagnostic accuracy but also on implementation context, threshold calibration, and integration into diagnostic pathways. We conducted a narrative, state-of-the-art review of AI applications across the TB diagnosis pathway. Evidence was synthesized from World Health Organization policy documents, independent validation initiatives, and peer-reviewed studies published between 2010 and 2026, with a structured selection process aligned with PRISMA principles. CAD for CXR is the most mature AI application and is recommended by WHO for TB screening and triage among individuals aged ≥15 years in specific contexts. Across studies, CAD-CXR demonstrates sensitivity comparable to human readers, although performance varies by product, population, and imaging conditions, necessitating local threshold calibration. Evidence from implementation studies suggests improvements in screening efficiency and potential cost-effectiveness in high-burden settings. Other AI modalities, including computed tomography (CT)-based imaging analysis, point-of-care ultrasound interpretation, cough or stethoscope sound analysis, clinical risk models, and genomic resistance prediction show promising but heterogeneous results, with most requiring further independent validation and prospective evaluation. AI has the potential to strengthen TB screening and diagnostic pathways, but its impact depends on integration into health systems and evaluated using patient- and program-level outcomes rather than accuracy alone. A differentiated approach is needed, with responsible scale-up of policy-endorsed tools alongside rigorous evaluation of emerging technologies to support effective and equitable TB care. Full article

This study proposes a unified multimodal temporal motion state perception framework for optical imaging-oriented biomedical applications, integrating visual skeleton sequences, inertial measurement unit (IMU) signals, and surface electromyography (EMG) signals. The framework utilizes modality-specific encoders and a cross-modal temporal alignment attention mechanism to explicitly model temporal offsets from heterogeneous sensing streams. A multimodal temporal Transformer backbone is introduced to capture long-range motion dependencies and cross-modal interactions, while an uncertainty-aware fusion module dynamically allocates weights based on modality confidence. Experimental results demonstrate that the proposed approach achieves an accuracy of 94.37%, an F1-score of 93.95%, and a mean average precision of 96.02%, outperforming mainstream baseline models. Robustness evaluations further confirm stable performance under visual occlusion and sensor noise. These results indicate that the framework provides a highly accurate and robust solution for rehabilitation assessment, sports training monitoring, and wearable intelligent interaction systems. Full article

Multifrequency operation in micromachined ultrasonic transducers, enabled by targeted excitation of specific vibrational modes, has emerged as an attractive approach for achieving tunable performance and configurability, well-suited for advanced ultrasound imaging and therapeutic applications. This paper presents a dual-electrode rectangular piezoelectric micromachined ultrasonic transducer (PMUT) designed for efficient dual-frequency operation through mode-selective actuation. The proposed architecture employs segmented electrodes that are spatially aligned with the strain distributions of two distinct flexural modes, enabling selective excitation of Mode 1 (fundamental) and Mode 3 (higher order) through appropriate electrode actuation. Finite element simulations and impedance analysis were used to guide the electrode configuration and validate the mode-selective behavior. The dual-mode PMUT was fabricated alongside a conventional single-electrode PMUT using identical membrane dimensions and material stack for direct comparison. Comprehensive electrical and underwater acoustic characterization confirmed that the conventional PMUT is limited to single-frequency operation at the fundamental resonance. In contrast, the proposed design achieved a substantial improvement in higher-order performance, with a threefold increase in acoustic pressure at Mode 3 compared to the conventional device. These results demonstrate that mode-aligned electrode segmentation enables efficient dual-mode operation without added fabrication complexity, making the design highly suitable for multifrequency ultrasonic applications such as biomedical imaging and sensing. Full article

Difference visual question answering (Diff-VQA) aims to answer questions by identifying and reasoning about differences between medical images. Existing methods often rely on simple feature subtraction or fusion to model image differences, while overlooking the asymmetric descriptive requirements of changed and unchanged cases and providing limited task-specific guidance to pretrained language decoders. To address these limitations, we propose D²MNet (Difference-aware Decoupling and Multi-prompt Network), a framework for medical Diff-VQA that combines change-aware reasoning with prompt-guided answer generation. Specifically, a Change Analysis Module (CAM) predicts whether a change is present and produces a binary change-aware prompt; a Difference-Aware Module (DAM) uses dual attention to capture fine-grained difference features; and a multi-prompt learning mechanism (MLM) injects question-aware, change-aware, and learnable prompts into the language decoder to improve contextual alignment and response generation. Experiments on the MIMIC-DiffVQA benchmark show that D2MNet achieves a CIDEr score of 2.907 ± 0.040, outperforming the strongest baseline, ReAl (2.409), under the same evaluation setting. These results demonstrate the effectiveness of the proposed design on benchmark medical Diff-VQA and suggest its potential for assisting difference-aware medical answer generation. Full article

Social networks such as Twitter have grown rapidly and are now flooded with sarcastic comments, both in text and in images. Detecting sarcasm in multimodal data has significant social value and is attracting increasing research attention. However, most studies overlook the role of sentiment, even though sentiment information in text is closely linked to clues of sarcasm. Additionally, few consider how text and images align semantically. To address these issues, we propose a sentiment-guided mutual learning network (SGMLN) for multimodal sarcasm detection. SGMLN utilizes sentiment information to inform the combination of text and image features, and employs mutual learning to facilitate knowledge sharing among classifiers. We design a sentiment-guided attention layer that injects sentiment into both modalities, producing features that capture sarcasm more effectively. Sentic-BERT extracts sentiment-aware vectors from text, using word-level sentiment as a mask. In mutual learning, a logistic distribution function measures differences between classifiers, improving knowledge transfer between modalities. This step boosts multimodal understanding and model performance. By introducing sentiment-aware representations and semantic alignment, SGMLN bridges the gap between text and images, making them more consistent. Experiments on public datasets demonstrate that our model is effective and outperforms alternatives. Full article

Even when an object’s color is accurately reproduced in a colorimetrically reproduced image (CRI), the perceived material appearance does not necessarily match that of the original object. This mismatch remains a challenge for faithfully reproducing real-world appearance in digital media. In this study, we investigated how lightness and chroma modulation affect the perception of glossiness, transparency, and roughness. These three attributes were quantitatively correlated with physical surface properties and image features through a direct comparison between objects and images. Observers selected the images that best matched the material appearance of the physical samples for each attribute. Image features derived from the gray-level co-occurrence matrix (GLCM) and surface roughness parameters were analyzed to compare the selected images with the CRI. In the lightness experiment, observers consistently selected images with higher lightness than the CRI, which was accompanied by increased complexity in the luminance distribution. In the chroma experiment, images with higher chroma were preferred; however, changes in GLCM features were negligible. Notably, stimuli with small local luminance differences at the CRI required larger shifts in image features to achieve perceptual matching. These findings indicate that modulating the luminance distribution is crucial for aligning the perceived appearance between physical objects and their digital representations. Full article

Strong light interference severely degrades imaging system performance. This paper presents a novel digital micromirror device (DMD)-based imaging system for robust, strong light suppression and long-distance detection. Our design strategically places the DMD at the primary image plane, utilizing a large F-number objective for extended depth of field. The relay imaging system employs a tilted image plane in a near-symmetric configuration to effectively balance DMD-induced aberrations, which avoids the off-axis layout and overall tilt of the relay system itself and greatly simplifies system alignment. Stray light analysis verifies the rationality of the structural design, and MTF tests confirm that the assembly performance of the prototype meets the design requirements. The system can achieve clear imaging of buildings at 1 km, which demonstrates its long-distance imaging capability. With an entrance pupil power density of 4.68 × 10⁻⁴ W/cm², strong light interference suppression has been successfully achieved via the DMD regional flipping method. This system offers an efficient solution for long-range imaging in strong light environments. Full article

Virtual try-on is a key enabling technology for online fashion retail and digital garment visualization. It aims to realistically render a target garment on a person while preserving geometric alignment and fine texture details. Appearance flow-based approaches provide explicit deformation modeling but often suffer from texture squeezing and boundary artifacts in challenging scenarios, such as long sleeves and tucked-in garments, especially under high-resolution settings. In this work, we propose StageAttn-VTON (Stage-wise Attentive Virtual Try-On), an appearance flow-based framework that improves structural coherence and visual fidelity through stage-wise deformation modeling. Specifically, garment warping is decomposed into three stages—coarse alignment, local refinement, and non-target region removal—which mitigates the coupling between competing objectives, such as smooth texture preservation and accurate structural alignment. Furthermore, we introduce a self-attention module in the image synthesis stage to enhance global dependency modeling and capture long-range garment–body interactions. Experiments on VITON-HD and the upper-body subset of DressCode demonstrate that StageAttn-VTON achieves consistently strong performance against representative warping-based and diffusion-based baselines. In addition, qualitative comparisons show that the proposed method better alleviates deformation artifacts in challenging regions such as sleeves and waist areas. Full article

As a key task in remote sensing analysis, semantic segmentation of remote sensing images (RSI) underpins many practical applications. Despite its importance, obtaining dense pixel-wise annotations remains labor-intensive and time-consuming. Unsupervised domain adaptation (UDA) offers a promising solution by utilizing knowledge from labeled source domains for unlabeled target domains, yet its effectiveness is often compromised by significant distribution shifts arising from variations in imaging conditions. To address this challenge, we propose a depth-aware adaptation network (DAAN), a novel two-branch network that explicitly leverages complementary depth information from a digital surface model (DSM) to enhance cross-domain remote sensing segmentation. Unlike conventional UDA methods that primarily focus on semantic features, DAAN incorporates depth data to build a more generalized feature space. This network introduces three key components: an adaptive feature aggregator (AFA) for progressive semantic-depth feature fusion, a gated prediction selection unit (GPSU) that selectively integrates predictions to mitigate the impact of noisy depth measurements, and misalignment-focused residual refinement (MFRR) module that emphasizes poorly aligned target regions during training. Experiments on the ISPRS and GAMUS datasets demonstrate the effectiveness of the proposed method. In particular, DAAN achieves an mIoU of 50.53% and an F1 score of 65.75% for cross-domain segmentation on ISPRS to GAMUS, outperforming models without depth information by 9.17% and 8.99%, respectively. These results demonstrate the advantage of integrating auxiliary geometric information to improve model generalization on unlabeled remote sensing datasets, contributing to higher mapping accuracy, more reliable automated analysis, and enhanced decision-making support. Full article

Background and Objectives: The association between spinal and pelvic alignment significantly impacts sagittal balance in adults. This study, that is retrospective, aims to investigate sagittal alignment anatomy of the pelvis and spine in juvenile idiopathic scoliosis (JIS) and adolescent idiopathic scoliosis (AIS) patients. Materials and Methods: We evaluated nine sagittal parameters from lateral radiographs of 100 JIS and AIS patients, including thoracic kyphosis (TKA), lumbar lordosis (LLA), pelvic tilt (PTA), pelvic incidence (PIA), spinosacral (SSA), sacral slope (SSLA), C7 tilt angles (C7-TA), sagittal vertical axis length (SVAL), and odontoid process hip axis angle (OPHAA) using the ImageJ program. Participants were classified based on their coronal curve group. Analysis of variance compared parameters between curve groups, and Pearson coefficients assessed the relationship between all parameters (p < 0.05). Results: Female participants had an average age of 13.4, and male participants had an average age of 13.0. Female participants had an average scoliosis degree of 19.3, while male participants had 15.2. PIA, PTA, SSLA, and SSA values were significantly higher in women participants than in men participants (p < 0.05). Additionally, PIA, PTA, SSLA, SSA, and OPHAA values were significantly lower in participants with a lower scoliosis degree (p < 0.05). We observed a moderately positive association between LLA and TKA, PIA, SSA, and C7-TA. There was also a moderate positive association between spinopelvic alignment parameters and the degree of scoliosis in participants. Conclusions: Easily measured values such as PIA, PTA, SSLA, SSA, and OPHAA may be related to severity of vertebral column deformities in patients, making them valuable for monitoring scoliosis patients. Full article

This study demonstrates a hierarchical spectral modelling approach for predicting pasture nutrition metrics using TabPFN (Tabular Prior-Data Fitted Network), a transformer-based machine learning architecture. In the face of climate variability, aligning stocking rates with pasture resources is crucial for sustainable livestock grazing, requiring accurate assessments of both pasture biomass and nutrient composition. Our research, conducted across diverse growth stages at five tropical and subtropical savanna rangeland properties in Queensland, Australia, with native and introduced C4 grasses, employed a hierarchical sampling and modelling strategy that scales from laboratory spectroscopy to Sentinel-2 satellite predictions via uncrewed aerial vehicle (UAV) hyperspectral imaging. Spectral data were collected from leaf (laboratory spectroscopy) through field (point measurements), UAV hyperspectral imaging, and Sentinel-2 satellite imagery. Traditional laboratory wet chemistry methods determined plant leaf and stem nutrient content, from which crude protein (CP = total nitrogen (TN) × 6.25) and dry matter digestibility (DMD = 88.9–0.779 × acid detergent fibre (ADF)) were derived. TabPFN models were trained at each spatial scale, achieving validation ${\mathrm{R}}^2$ of 0.76 for crude protein at the leaf scale, 0.95 at the UAV scale, and 0.92 at the Sentinel-2 satellite scale. For dry matter digestibility, validation ${\mathrm{R}}^2$ was 0.88 at the UAV scale and 0.73 at the Sentinel-2 scale. A pasture classification masking approach using a deep neural network with 98.6% accuracy (7 classes) was implemented to focus predictions on productive pasture areas, excluding bare soil and woody vegetation. The Sentinel-2 models were trained on 462 samples from 19 site–date combinations across 11 field sites. The TabPFN architecture provided notable advantages over traditional neural networks: no hyperparameter tuning required, faster training, and superior generalisation from limited training samples. These results demonstrate the potential for accurate and efficient prediction and mapping of pasture quality across large areas (100 s–1000 s ${\mathrm{k}\mathrm{m}}^2$) using freely available satellite imagery and open-source machine learning frameworks. Full article

Gliomas are generally readily detected and broadly characterized using conventional MRI; however, substantial challenges remain in accurately delineating tumor extent, grading heterogeneous disease, and translating imaging findings into consistent, reproducible clinical decisions. Despite reported Dice coefficients of 0.85–0.91 for whole-tumor segmentation and classification AUC values exceeding 0.90 for glioma grading in curated datasets, most AI systems remain limited by validation design, dataset bias, and inadequate external generalizability. This narrative review synthesizes current AI applications for MRI-based glioma detection and segmentation, highlighting the evolution from radiomics-based classical machine learning approaches relying on handcrafted features to deep learning models capable of end-to-end representation learning. Commonly used MRI sequences, algorithmic paradigms, and reported performance trends are reviewed, with particular emphasis on tumor segmentation as a foundational enabling task. Key limitations that hinder clinical translation are examined, including limited dataset diversity, validation practices that inflate reported performance, domain shift across institutions, acquisition-related bias, and inadequate model interpretability. Emerging strategies to address these challenges, such as multi-institutional training, harmonization techniques, explainable AI frameworks, and workflow-integrated validation, are also discussed. While AI-based models demonstrate strong technical performance in research settings, their clinical impact will depend on rigorous external validation, transparency, and alignment with real-world neuro-oncology workflows. Full article

The growing demand for Critical Raw Materials (CRMs) requires mining practices that align with sustainability and environmental, social, and governance (ESG) principles, while mining training increasingly benefits from advanced digital tools. Virtual Reality (VR) can provide high-resolution site representations that support both interactive learning and data-oriented analysis without operational risk. This study presents a VR-based framework for the quantitative assessment of pit lake rehabilitation using Virtual Excursions (VEs) developed from panoramic imagery and supported by machine-learning correction. High-resolution 360° panoramic images were used to extract geometric characteristics of a rehabilitated pit lake at the LARCO GMMSA Euboea mine site, Greece, including surface area, shoreline length, mean diameter, and maximum diameter. These image-derived estimates were validated against ground-truth data from field surveys and mine-closure documentation. To reduce systematic deviations associated with panoramic image measurements, a supervised multiple linear regression model was applied as a correction step. Validation based on Root Mean Square Error (RMSE) and the coefficient of determination ($R^2$) showed substantial improvement of the corrected estimates relative to the uncorrected image-based measurements. The results demonstrate that panoramic VR imagery can support site-specific quantitative environmental assessment in addition to its educational value. Although the present findings are limited to a single pit lake case study, the proposed workflow provides a structured basis for integrating immersive visualization, image-based measurement, and regression-based correction in post-mining rehabilitation assessment. Full article