Search Results (227)

Background: Lung cancer ranks as the leading cause of cancer-related mortality worldwide. The complexity of tumor delineation, crucial for radiation therapy, requires expertise often unavailable in resource-limited settings. Artificial Intelligence (AI), particularly with advancements in deep learning (DL) and natural language processing (NLP), offers potential solutions yet is challenged by high false positive rates. Purpose: The Oncology Contouring Copilot (OCC) system is developed to leverage oncologist expertise for precise tumor contouring using textual descriptions, aiming to increase the efficiency of oncological workflows by combining the strengths of AI with human oversight. Methods: Our OCC system initially identifies nodule candidates from CT scans. Employing Language Vision Models (LVMs) like GPT-4V, OCC then effectively reduces false positives with clinical descriptive texts, merging textual and visual data to automate tumor delineation, designed to elevate the quality of oncology care by incorporating knowledge from experienced domain experts. Results: The deployment of the OCC system resulted in a 35.0% reduction in the false discovery rate, a 72.4% decrease in false positives per scan, and an F1-score of 0.652 across our dataset for unbiased evaluation. Conclusions: OCC represents a significant advance in oncology care, particularly through the use of the latest LVMs, improving contouring results by (1) streamlining oncology treatment workflows by optimizing tumor delineation and reducing manual processes; (2) offering a scalable and intuitive framework to reduce false positives in radiotherapy planning using LVMs; (3) introducing novel medical language vision prompt techniques to minimize LVM hallucinations with ablation study; and (4) conducting a comparative analysis of LVMs, highlighting their potential in addressing medical language vision challenges. Full article

Large Vision Language Models (LVLMs) have shown promise in remote sensing applications, yet struggle with “uncommon” objects that lack sufficient public labeled data. This paper presents Enhanced-RSCLIP, a novel dual-prompt architecture that combines text prompting with exemplar-image processing for cattle herd detection in satellite imagery. Our approach introduces a key innovation where an exemplar-image preprocessing module using crop-based or attention-based algorithms extracts focused object features which are fed as a dual stream to a contrastive learning framework that fuses textual descriptions with visual exemplar embeddings. We evaluated our method on a custom dataset of 260 satellite images across UK and Nigerian regions. Enhanced-RSCLIP with crop-based exemplar processing achieved 72% accuracy in cattle detection and 56.2% overall accuracy on cross-domain transfer tasks, significantly outperforming text-only CLIP (31% overall accuracy). The dual-prompt architecture enables effective few-shot learning and cross-regional transfer from data-rich (UK) to data-sparse (Nigeria) environments, demonstrating a 41% improvement over baseline approaches for uncommon object detection in satellite imagery. Full article

Precise medical image segmentation is crucial for advancing computer-aided diagnosis. Although deep learning-based medical image segmentation is now widely applied in this field, the complexity of human anatomy and the diversity of pathological manifestations often necessitate the use of image annotations to enhance segmentation accuracy. In this process, the scarcity of annotations and the lightweight design requirements of associated text encoders collectively present key challenges for improving segmentation model performance. To address these challenges, we propose MedLangViT, a novel language–vision multimodal model for medical image segmentation that incorporates medical descriptive information through lightweight text embedding rather than text encoders. MedLangViT innovatively leverages medical textual information to assist the segmentation process, thereby reducing reliance on extensive high-precision image annotations. Furthermore, we design an Enhanced Channel-Spatial Attention Module (ECSAM) to effectively fuse textual and visual features, strengthening textual guidance for segmentation decisions. Extensive experiments conducted on two publicly available text–image-paired medical datasets demonstrated that MedLangViT significantly outperforms existing state-of-the-art methods, validating the effectiveness of both the proposed model and the ECSAM. Full article

Loess deposits in China, covering extensive regions, exhibit distinctive physical and mechanical characteristics, including collapsibility and reduced mechanical strength. These properties contribute to heightened susceptibility to slope-related geological hazards, such as landslides and collapses, in these areas. The widespread distribution and challenging prevention of these geological disasters have emerged as significant impediments to both public safety and economic development in China. Moreover, geological disaster data originates from diverse sources and exists in substantial fragmented, decentralized, and unstructured formats, including textual records and graphical representations. These datasets exhibit complex structures and heterogeneous formats yet suffer from inadequate organization and storage due to the absence of unified descriptive standards. The lack of systematic categorization and standardized representation significantly hinders effective data integration and knowledge extraction across different sources. To address these challenges, this study proposes a novel loess slope stability assessment method employing a dendrogram neural network (GNN-TreeNet) integrated with knowledge graph technology. The methodology progresses through three phases: (1) construction of a multi-domain knowledge graph integrating a large number of loess slopes with historical disaster records, instability factor relationships, and empirical parameter correlations; (2) generation of expressive node embeddings capturing inherent connections via graph neural networks; (3) development and training of the GNN-TreeNet architecture that leverages the graph’s enhanced representation capacity for stability evaluation. This structured framework enables cross-disciplinary data synthesis and interpretable slope stability analysis through a systematic integration of geological, geographical, and empirical knowledge components. Full article

The use of intelligent crop recommendation systems has become crucial in the era of smart agriculture to increase yield and enhance resource utilization. In this study, we compared different machine learning (ML), and deep learning (DL) models utilizing structured tabular data for crop recommendation. During our experimentation, both ML and DL models achieved decent performance. However, their architectures are not suited for setting up conversational systems. To overcome this limitation, we converted the structured tabular data to descriptive textual data and utilized it to fine-tune Large Language Models (LLMs), including BERT and GPT-2. In comprehensive experiments, we demonstrated that GPT-2 achieved a higher accuracy of 99.55% than the best-performing ML and DL models, while maintaining precision of 99.58% and recall of 99.55%. We also demonstrated that GPT-2 not only keeps up competitive accuracy but also offers natural language interaction capabilities. Due to this capability, it is a viable option to be used for real-time agricultural decision support systems. Full article

Substation equipment defect detection is a critical aspect of ensuring the reliability and stability of modern power grids. However, existing deep-learning-based detection methods often face significant challenges in real-world deployment, primarily due to low detection accuracy and inconsistent anomaly definitions across different substation environments. To address these limitations, this paper proposes the Language-Guided Enhanced Anomaly Power Equipment Detection Network (LEAD-Net), a novel framework that leverages text-guided learning during training to significantly improve defect detection performance. Unlike traditional methods, LEAD-Net integrates textual descriptions of defects, such as historical maintenance records or inspection reports, as auxiliary guidance during training. A key innovation is the Language-Guided Anomaly Feature Enhancement Module (LAFEM), which refines channel attention using these text features. Crucially, LEAD-Net operates solely on image data during inference, ensuring practical applicability. Experiments on a real-world substation dataset, comprising 8307 image–text pairs and encompassing a diverse range of defect categories encountered in operational substation environments, demonstrate that LEAD-Net significantly outperforms state-of-the-art object detection methods (Faster R-CNN, YOLOv9, DETR, and Deformable DETR), achieving a mean Average Precision (mAP) of 79.51%. Ablation studies confirm the contributions of both LAFEM and the training-time text guidance. The results highlight the effectiveness and novelty of using training-time defect descriptions to enhance visual anomaly detection without requiring text input at inference. Full article

In the landslide chain from pre-disaster conditions to landslide mitigation and recovery, time is an important factor in understanding the geological hazards process and managing landsides. Static knowledge graphs are unable to capture the temporal dynamics of landslide events. To address this limitation, we propose a systematic framework for constructing a multi-temporal knowledge graph of landslides that integrates multi-source temporal data, enabling the dynamic tracking of landslide processes. Our approach comprises three key steps. First, we summarize domain knowledge and develop a temporal ontology model based on the disaster chain management system. Second, we map heterogeneous datasets (both tabular and textual data) into triples/quadruples and represent them based on the RDF (Resource Description Framework) and quadruple approaches. Finally, we validate the utility of multi-temporal knowledge graphs through multidimensional queries and develop a web interface that allows users to input landslide names to retrieve location and time-axis information. A case study of the Zhangjiawan landslide in the Three Gorges Reservoir Area demonstrates the multi-temporal knowledge graph’s capability to track temporal updates effectively. The query results show that multi-temporal knowledge graphs effectively support multi-temporal queries. This study advances landslide research by combining static knowledge representation with the dynamic evolution of landslides, laying the foundation for hazard forecasting and intelligent early-warning systems. Full article

Poultry feces, a critical biomarker for health assessment, requires timely and accurate pathological identification for food safety. Conventional visual-only methods face limitations due to environmental sensitivity and high visual similarity among feces from different diseases. To address this, we propose MMCD (Multimodal Chicken-feces Diagnosis), a ResNet50-based multimodal fusion model leveraging semantic complementarity between images and descriptive text to enhance diagnostic precision. Key innovations include the following: (1) Integrating MASA(Manhattan self-attention)and DSconv (Depthwise Separable convolution) into the backbone network to mitigate feature confusion. (2) Utilizing a pre-trained BERT to extract textual semantic features, reducing annotation dependency and cost. (3) Designing a lightweight Gated Cross-Attention (GCA) module for dynamic multimodal fusion, achieving a 41% parameter reduction versus cross-modal transformers. Experiments demonstrate that MMCD significantly outperforms single-modal baselines in Accuracy (+8.69%), Recall (+8.72%), Precision (+8.67%), and F1 score (+8.72%). It surpasses simple feature concatenation by 2.51–2.82% and reduces parameters by 7.5M and computations by 1.62 GFLOPs versus the base ResNet50. This work validates multimodal fusion’s efficacy in pathological fecal detection, providing a theoretical and technical foundation for agricultural health monitoring systems. Full article

Many radar applications rely primarily on visual classification for their evaluations. However, new research is integrating textual descriptions alongside visual input and showing that such multimodal fusion improves contextual understanding. A critical issue in this area is the effective alignment of coded text with corresponding images. To this end, our paper presents an adversarial training framework that generates descriptive text from the latent space of a visual radar classifier. Our quantitative evaluations show that this dual-task approach maintains a robust classification accuracy of 98.3% despite the inclusion of Gaussian-distributed latent spaces. Beyond these numerical validations, we conduct a qualitative study of the text output in relation to the classifier’s predictions. This analysis highlights the correlation between the generated descriptions and the assigned categories and provides insight into the classifier’s visual interpretation processes, particularly in the context of normally uninterpretable radar data. Full article

Object detection in drone-captured imagery has attracted significant attention due to its wide range of real-world applications, including surveillance, disaster response, and environmental monitoring. Although the majority of existing methods are developed under closed-set assumptions, and some recent studies have begun to explore open-vocabulary or open-world detection, their application to UAV imagery remains limited and underexplored. In this paper, we address this limitation by exploring the relationship between images and textual semantics to extend object detection in UAV imagery to an open-vocabulary setting. We propose a novel and efficient detector named Unmanned Aerial Vehicle Open-Vocabulary Detector (UAV-OVD), specifically designed for drone-captured scenes. To facilitate open-vocabulary object detection, we propose improvements from three complementary perspectives. First, at the training level, we design a region–text contrastive loss to replace conventional classification loss, allowing the model to align visual regions with textual descriptions beyond fixed category sets. Structurally, building on this, we introduce a multi-level text-guided fusion decoder that integrates visual features across multiple spatial scales under language guidance, thereby improving overall detection performance and enhancing the representation and perception of small objects. Finally, from the data perspective, we enrich the original dataset with synonym-augmented category labels, enabling more flexible and semantically expressive supervision. Experiments conducted on two widely used benchmark datasets demonstrate that our approach achieves significant improvements in both mean mAP and Recall. For instance, for Zero-Shot Detection on xView, UAV-OVD achieves 9.9 mAP and 67.3 Recall, 1.1 and 25.6 higher than that of YOLO-World. In terms of speed, UAV-OVD achieves 53.8 FPS, nearly twice as fast as YOLO-World and five times faster than DetrReg, demonstrating its strong potential for real-time open-vocabulary detection in UAV imagery. Full article

Wallboard outsourcing is a critical task in cloud-based manufacturing, where demand enterprises seek suitable suppliers for machining services through online platforms. However, the recommendation process faces significant challenges, including sparse rating data, unstructured textual descriptions from suppliers, and complex, non-linear user preferences. To address these issues, this paper proposes AttVAE-PMF, a novel recommendation method based on dual-channel neural networks and probabilistic matrix factorization. Specifically, an attention-enhanced long short-term memory (LSTM) is employed to extract semantic features from free-text supplier descriptions, while a variational autoencoder (VAE) is used to model latent preferences from sparse demand-side ratings. These two types of latent representations are then fused via probabilistic matrix factorization (PMF) to complete the rating matrix and infer enterprise preferences. Experiments conducted on both the wallboard dataset and the MovieLens-100K dataset demonstrate that AttVAE-PMF outperforms baseline methods—including PMF, DLCRS, and SSAERec—in terms of convergence speed and robustness to data sparsity, validating its effectiveness in handling sparse and heterogeneous information in wallboard outsourcing recommendation scenarios. Full article

The automation of smart building design processes remains a significant challenge, particularly in translating complex natural language requirements into structured design parameters within Computer-Aided Design (CAD) environments. Traditional design workflows rely heavily on manual input, which can be inefficient, error-prone, and time-consuming, limiting the integration of adaptive, real-time inputs. To address this issue, this study proposes an intelligent Natural Language Processing (NLP)-based workflow for automating the conversion of design briefs into CAD-readable parameters. This study proposes a five-step integration framework that utilizes NLP to extract key design requirements from unstructured inputs such as emails and textual descriptions. The framework then identifies optimal integration points—such as APIs, direct database connections, or plugin-based solutions—to ensure seamless adaptability across various CAD systems. The implementation of this workflow has the potential to enable the automation of routine design tasks, reducing the reliance on manual data entry and enhancing efficiency. The key findings demonstrate that the proposed NLP-based approach may significantly streamline the design process, minimize human intervention while maintaining accuracy and adaptability. By integrating NLP with CAD environments, this study contributes to advancing intelligent design automation, ultimately supporting more efficient, cost-effective, and scalable smart building development. These findings highlight the potential of NLP to bridge the gap between human input and machine-readable data, providing a transformative solution for the architectural and construction industries. Full article

Earth observation data serve as a fundamental resource in Earth system science. The rapid advancement of remote sensing and in situ measurement technologies has led to the generation of massive volumes of data, accompanied by a growing body of geographic textual information. Efficient and accurate classification and management of these geographic texts has become a critical challenge in the field. However, the effectiveness of traditional classification approaches is hindered by several issues, including data sparsity, class imbalance, semantic ambiguity, and the prevalence of domain-specific terminology. To address these limitations and enable the intelligent management of geographic information, this study proposes an efficient geographic text classification framework based on large language models (LLMs), tailored to the unique semantic and structural characteristics of geographic data. Specifically, LLM-based data augmentation strategies are employed to mitigate the scarcity of labeled data and class imbalance. A semantic vector database is utilized to filter the label space prior to inference, enhancing the model’s adaptability to diverse geographic terms. Furthermore, few-shot prompt learning guides LLMs in understanding domain-specific language, while an output alignment mechanism improves classification stability for complex descriptions. This approach offers a scalable solution for the automated semantic classification of geographic text for unlocking the potential of ever-expanding geospatial big data, thereby advancing intelligent information processing and knowledge discovery in the geospatial domain. Full article

Prior research has focused on the technical and institutional challenges of blockchain adoption. However, little is known about how blockchain ventures claim categorical space in the market and how such domain positioning influences their visibility and evaluation. This study investigates the relationship between strategic domain positioning and market recognition among blockchain-based ventures, with a particular focus on applications relevant to e-commerce, such as non-fungible tokens (NFTs) and decentralized finance (DeFi). Drawing on research on categorization, legitimacy, and the technology lifecycle, we propose a domain lifecycle perspective that accounts for the evolving expectations and legitimacy criteria across blockchain domains. Using BERTopic, a transformer-based topic modeling method, we classify 9665 blockchain ventures based on their textual business descriptions. We then test the impact of domain positioning on market recognition—proxied by Crunchbase rank—while examining the moderating effects of external validation signals such as funding events, media attention, and organizational age. Our findings reveal that clear domain positioning significantly enhances market recognition, but the strength and direction of this effect vary by domain. Specifically, NFT ventures experience stronger recognition when young and less institutionally validated, suggesting a novelty premium, while DeFi ventures benefit more from conventional legitimacy signals. These results advance our understanding of how categorical dynamics operate in emerging digital ecosystems and offer practical insights for e-commerce platforms, investors, and entrepreneurs navigating blockchain-enabled innovation. Full article

Text-based person search (TPS), a critical technology for security and surveillance, aims to retrieve target individuals from image galleries using textual descriptions. The existing methods face two challenges: (1) ambiguous attribute–noun association (AANA), where syntactic ambiguities lead to incorrect associations between attributes and the intended nouns; and (2) textual noise and relevance imbalance (TNRI), where irrelevant or non-discriminative tokens (e.g., ‘wearing’) reduce the saliency of critical visual attributes in the textual description. To address these aspects, we propose the dependency-aware entity–attribute alignment network (DEAAN), a novel framework that explicitly tackles AANA through dependency-guided attention and TNRI via adaptive token filtering. The DEAAN introduces two modules: (1) dependency-assisted implicit reasoning (DAIR) to resolve AANA through syntactic parsing, and (2) relevance-adaptive token selection (RATS) to suppress TNRI by learning token saliency. Experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid demonstrate state-of-the-art performance, with the DEAAN achieving a Rank-1 accuracy of 76.71% and an mAP of 69.07% on CUHK-PEDES, surpassing RDE by 0.77% in Rank-1 and 1.51% in mAP. Ablation studies reveal that DAIR and RATS individually improve Rank-1 by 2.54% and 3.42%, while their combination elevates the performance by 6.35%, validating their synergy. This work bridges structured linguistic analysis with adaptive feature selection, demonstrating practical robustness in surveillance-oriented TPS scenarios. Full article