Expert Systems最新文献_第6页

M2M-GD: Integrating Gradient Guidance and Diffusion Mechanisms in Decomposition-Based Multi-Objective Optimization M2M-GD：基于分解的多目标优化中梯度引导和扩散机制的集成

IF 3.4 4区计算机科学

Expert Systems Pub Date : 2026-07-28 DOI: 10.1111/exsy.70379

Xiangkun Qiu, Lei Chen, Hai-Lin Liu

{"title":"M2M-GD: Integrating Gradient Guidance and Diffusion Mechanisms in Decomposition-Based Multi-Objective Optimization","authors":"Xiangkun Qiu, Lei Chen, Hai-Lin Liu","doi":"10.1111/exsy.70379","DOIUrl":"https://doi.org/10.1111/exsy.70379","url":null,"abstract":"<div>\u0000 \u0000 <p>The multi-objective to multi-objective (M2M) decomposition strategy can effectively maintain population diversity in evolutionary multi-objective optimization by handling the decomposed subproblems in parallel within geometric partitioned objective space. However, existing approaches are hindered by the slow convergence from random evolutionary operators and a lack of collaboration between subproblems when handling complex Pareto front (PF) shapes. To address this issue, this paper proposes the M2M-GD, a novel algorithm that comprehensively improves the M2M framework with three different strategies. First, we incorporate a gradient guidance mechanism that utilizes directional information to expedite convergence. Second, we devise a gradient diffusion strategy that enables knowledge transfer among subproblems through a dynamically updated matrix, promoting synergistic collaboration. Coupled with adaptive parameter control, these innovations collectively provide a more realistic convergence guarantee for the proposed M2M-GD. Empirical results on MOEADM2M, DTLZ and WFG benchmark problems confirm that M2M-GD achieves superior performance in both convergence and diversity compared to existing state-of-the-art algorithms.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 9","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148616315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SmartTur+ECO: A Multimodal Conversational Recommender System Integrating Virtual Reality and Gamification for Smart Tourism smartturr +ECO：融合虚拟现实和游戏化的智能旅游多模式会话推荐系统

IF 3.4 4区计算机科学

Expert Systems Pub Date : 2026-07-28 DOI: 10.1111/exsy.70371

Juan Carlos Carrillo, Victoria Beltran, Laura Sebastia, Eva Onaindia, Ignacio Seguí, Alfonso Lopez, Jose Carlos Sola

{"title":"SmartTur+ECO: A Multimodal Conversational Recommender System Integrating Virtual Reality and Gamification for Smart Tourism","authors":"Juan Carlos Carrillo, Victoria Beltran, Laura Sebastia, Eva Onaindia, Ignacio Seguí, Alfonso Lopez, Jose Carlos Sola","doi":"10.1111/exsy.70371","DOIUrl":"https://doi.org/10.1111/exsy.70371","url":null,"abstract":"<p>This paper presents SmartTur+ECO, a system for tourist attractions that integrates conversational recommendation systems (CRS), virtual reality (VR) and gamification. It efficiently gathers trip data and elicits user preferences through interactions with a chatbot, addressing the user-cold start problem common in tourism. Using an exploit-explore approach with sentence embeddings from POI descriptions, SmartTur+ECO provides precise and personalized recommendations organized into multi-day plans, considering opening hours and locations. VR integration offers immersive pre-trip experiences, helping users make informed decisions. Gamification elements like mini-games and rewards are designed to foster user engagement and motivation. SmartTur+ECO's modular and scalable architecture ensures compatibility with various devices and allows for the easy integration of new algorithms and data sources, with the aim of supporting recommendation processes. This innovative combination sets new standards in tourism by making travel planning more efficient, entertaining and meaningful.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 9","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70371","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148616422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FIRFormer: Transformer With Frequency-Aware Fusion and Recalibrated Attention for Time Series Forecasting FIRFormer：用于时间序列预测的具有频率感知融合和重新校准注意力的变压器

IF 3.4 4区计算机科学

Expert Systems Pub Date : 2026-07-26 DOI: 10.1111/exsy.70378

Shijun Chen, Hua Wang, Fan Zhang

{"title":"FIRFormer: Transformer With Frequency-Aware Fusion and Recalibrated Attention for Time Series Forecasting","authors":"Shijun Chen, Hua Wang, Fan Zhang","doi":"10.1111/exsy.70378","DOIUrl":"https://doi.org/10.1111/exsy.70378","url":null,"abstract":"<div>\u0000 \u0000 <p>The effectiveness of Transformers in time series forecasting largely depends on their ability to extract and utilise key features. The model not only needs to capture temporal patterns but also focus its attention on the most informative inputs, thereby constructing sharp and discriminative attention distributions to highlight critical information and improve forecasting accuracy. However, despite their strengths in modelling global dependencies, conventional Transformers remain limited in capturing predictive key patterns and forming highly distinctive attention weights. To address this limitation, we propose FIRFormer, a framework that enhances input representation and reconstructs the attention mechanism to better capture important temporal dynamics. Specifically, we introduce the Dynamic Frequency Selector module to adaptively filter frequency components most relevant to the forecasting objective, reducing redundancy and improving input efficiency. Subsequently, we introduce the Biased Integration Window module, which integrates a temporal decay mechanism into sliding aggregation to strengthen the correlations within local contexts, achieves precise fusion of temporal dynamic patterns and further emphasises the modelling value of recent critical information. Finally, we propose the Attention Recalibration module, which employs a dual-branch attention refinement strategy. It enhances attention selectivity from both the local feature perspective and the global subspace perspective, promoting sharper and more focused attention distributions. FIRFormer enhances the perception of critical dynamic patterns and achieves performance improvements across multiple real-world forecasting tasks.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 9","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148615913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

History, Development, and Principles of Representation Learning—An Introductory Survey 表征学习的历史、发展和原理——概论

IF 3.4 4区计算机科学

Expert Systems Pub Date : 2026-07-24 DOI: 10.1111/exsy.70370

Zhiyong Wang, Qiang He, Jun Mou, Wei Wang, Junxin Chen

{"title":"History, Development, and Principles of Representation Learning—An Introductory Survey","authors":"Zhiyong Wang, Qiang He, Jun Mou, Wei Wang, Junxin Chen","doi":"10.1111/exsy.70370","DOIUrl":"https://doi.org/10.1111/exsy.70370","url":null,"abstract":"<div>\u0000 \u0000 <p>Representation learning has become a cornerstone of artificial intelligence, designed to automatically extract low-dimensional, meaningful features from high-dimensional, sparse raw data. By drastically reducing the reliance on manual feature engineering, representation learning enhances model performance across a wide range of tasks. The field has evolved significantly over the past decades, transitioning from early linear methods, such as Principal Component Analysis (PCA), to modern deep learning paradigms powered by neural networks, generative adversarial networks (GANs), and pre-trained models. Although the rapid development of representation learning has significantly promoted the progress of natural language processing (NLP), computer vision, and recommender systems, the general practitioners still have a poor understanding of its historical background, core principles, and wide range of applications. To some extent, this limits the full development of its potential. To this end, this survey aims to provide a comprehensive and easily understandable overview for a wider audience. This survey conducts a systematic literature review to tease out the evolution of representation learning and analyse its core drivers. At the same time, this survey deeply explains the basic principles of representation learning, and introduces its practical application cases in various fields. This survey also points out the main limitations of current models and prospects the future research directions.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 9","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148616058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TESA-Net: A Court-Aware Architecture for Flow-Free Basketball Action Recognition TESA-Net：一个无流篮球动作识别的球场感知架构

IF 3.4 4区计算机科学

Expert Systems Pub Date : 2026-07-23 DOI: 10.1111/exsy.70380

Andrea F. Abate, Michele Nappi, Chiara Pero, Gianluca Ronga

{"title":"TESA-Net: A Court-Aware Architecture for Flow-Free Basketball Action Recognition","authors":"Andrea F. Abate, Michele Nappi, Chiara Pero, Gianluca Ronga","doi":"10.1111/exsy.70380","DOIUrl":"https://doi.org/10.1111/exsy.70380","url":null,"abstract":"<div>\u0000 \u0000 <p>Human action recognition in sports videos is a challenging computer vision task due to fast motion, frequent occlusions and fine-grained visual similarities among action classes. This work presents TESA-Net (Temporal-Efficient Spatial Attention Network), an efficient dual-stream architecture for basketball action recognition that achieves state-of-the-art performance while maintaining computational efficiency. Unlike existing methods that rely on expensive 3D convolutions or full spatio-temporal attention mechanisms, TESA-Net employs a pre-trained 2D ResNet-50 backbone with lightweight temporal aggregation. The key innovation is a novel Court Line Detection module that augments the appearance stream with edge-based geometric features, enabling accurate discrimination between shot types that differ primarily in shooting distance. We evaluate TESA-Net on two complementary benchmarks: Basketball-51, which targets fine-grained shot classification in professional broadcasts, and MultiSubjects, which addresses coarse-grained action recognition in amateur gymnasium recordings. On Basketball-51, TESA-Net achieves a validation accuracy of 94.37%, surpassing the previous state-of-the-art HAQT (92.76%) by 1.61 percentage points. On MultiSubjects, TESA-Net reaches 96.12% accuracy, matching transformer-based approaches while using significantly fewer parameters. Owing to its efficient design, TESA-Net requires substantially less memory than competing 3D-based methods, enabling practical deployment without high-end hardware.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 9","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148615578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AA-SHAP: Superpixel Affinity for Explainable Image Classification AA-SHAP：用于可解释图像分类的超像素亲和性

IF 3.4 4区计算机科学

Expert Systems Pub Date : 2026-07-22 DOI: 10.1111/exsy.70376

Vahidin Hasić, Amar Halilović, Senka Krivić

{"title":"AA-SHAP: Superpixel Affinity for Explainable Image Classification","authors":"Vahidin Hasić, Amar Halilović, Senka Krivić","doi":"10.1111/exsy.70376","DOIUrl":"https://doi.org/10.1111/exsy.70376","url":null,"abstract":"<div>\u0000 \u0000 <p>Explainable AI (XAI) is essential for building trust in Deep Neural Networks (DNNs). SHAP (SHapley Additive exPlanations) is a well-known XAI technique for attributing feature importance, but it struggles with exponential computational complexity as the number of features increases. Various approximation methods have been suggested, but they compromise SHAP's theoretical principles. We introduce AA-SHAP, a novel approach that derives superpixel affinity from the explained model's internals to identify and group superpixels. AA-SHAP constructs a relevance-consistency affinity between superpixel interdependence, enabling much faster SHAP calculations on a reduced set of meta-superpixels while outperforming previous methods in explanation faithfulness. Exact Shapley values are computed on the reduced meta-superpixel game, preserving all axiomatic guarantees within the aggregated feature space. Evaluated across multiple datasets, both convolutional and transformer classification architectures show that AA-SHAP produces more faithful attributions than competing methods while improving computational speed and maintaining SHAP's theoretical axioms. The source code is available at https://github.com/vhasic/AA-SHAP.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 9","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148615729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mamba-SBRNet: Real-Time Lightweight Student Behaviour Object Detection Model Mamba-SBRNet：实时轻量级学生行为对象检测模型

IF 3.4 4区计算机科学

Expert Systems Pub Date : 2026-07-22 DOI: 10.1111/exsy.70372

Le Zou, Jian Jin, Yuanhang Xia, Fengling Jiang, Yimin Wu, Kia Dashtipour, Mandar Gogate, Amir Hussain, Xiaofeng Wang

{"title":"Mamba-SBRNet: Real-Time Lightweight Student Behaviour Object Detection Model","authors":"Le Zou, Jian Jin, Yuanhang Xia, Fengling Jiang, Yimin Wu, Kia Dashtipour, Mandar Gogate, Amir Hussain, Xiaofeng Wang","doi":"10.1111/exsy.70372","DOIUrl":"https://doi.org/10.1111/exsy.70372","url":null,"abstract":"<div>\u0000 \u0000 <p>Detecting student behaviour objects in classroom environments is crucial for assessing educational progress, optimizing teaching strategies and improving student learning outcomes. With the ongoing advancement of educational informatization, analysing classroom behaviour has become an important tool for enhancing teaching quality and personalized learning. However, current student behaviour object detection models based on CNN and Transformer architectures face challenges such as large parameter sizes and high inference delays when deployed on edge devices in classrooms, limiting their practical application. To address these issues, this study proposes a lightweight student behaviour detection framework based on the Mamba architecture, aimed at balancing computational efficiency and detection accuracy. First, the framework based on the state-space model (SSM) efficiently captures global dependencies, using local convolutions to enhance detection accuracy and scene understanding while maintaining real-time performance. Second, the C2CGA module increases attention diversity through feature splitting, self-attention, cascading and projected concatenation, deepening the network while reducing computational overhead. Finally, the A2CMoCA module aggregates multi-scale features, improving the learning of small objects and occluded behaviours. Experiments on a self-built classroom behaviour dataset (containing eight typical teaching behaviours) show that the proposed method achieves 91.5% detection accuracy while maintaining a lightweight design. Compared to the baseline model, its computational efficiency (5.9G FLOPs) is reduced by 56.6%, the parameter size is compressed to 3.65 M (a 39% reduction) and the inference speed is 3.2 ms, meeting the real-time monitoring requirements in classroom teaching scenarios.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 9","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148615694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AEN-GCL: Aspect-Guided Embedding and Negative Sampling With Graph Contrastive Learning for Recommendation 基于图对比学习的面向推荐的方面引导嵌入和负抽样

IF 3.4 4区计算机科学

Expert Systems Pub Date : 2026-07-22 DOI: 10.1111/exsy.70377

Yao Xu, Xian Mu, Yi Ren, Yuntao Zou, Dagang Li

{"title":"AEN-GCL: Aspect-Guided Embedding and Negative Sampling With Graph Contrastive Learning for Recommendation","authors":"Yao Xu, Xian Mu, Yi Ren, Yuntao Zou, Dagang Li","doi":"10.1111/exsy.70377","DOIUrl":"https://doi.org/10.1111/exsy.70377","url":null,"abstract":"<div>\u0000 \u0000 <p>Graph neural networks enhance collaborative signals through multi-hop message passing, achieving promising results in recommender systems. Nevertheless, several challenges still remain. Most existing methods rely solely on user-item interactions, which are insufficient to capture users' fine-grained preferences. Although some approaches exploit aspect information to alleviate this issue, they typically treat aspects as auxiliary information and fail to explicitly integrate them into user (item) embeddings. Additionally, these methods generally treat all unobserved items as negative samples and employ a uniform sampling strategy. However, due to the inherent popularity bias of items, such a negative sampling strategy is suboptimal for effective model training. To address the above issues, we propose a novel method, AEN-GCL, which leverages aspect information to help construct the initial embeddings of users (items) and guide negative sampling, while incorporating a self-supervised auxiliary learning task. Specifically, we first employ a pre-trained Sentence-BERT to compute the similarities between reviews and predefined seed sentences of each aspect. The similarities derived from the reviews of each user (item) are aggregated to form an aspect representation, which is combined with category information to construct the initial embedding. Next, we compute the aspect-level similarity between the user, the positive item and candidate negatives generated by an adaptive category-based strategy. The user-aware and item-aware similarities are jointly used to guide negative sampling. In addition, to alleviate sparse supervision signals, we incorporate edge-dropout-based graph contrastive learning to enhance model training. Comprehensive experiments on three public datasets demonstrate that the proposed AEN-GCL achieves competitive performance compared with state-of-the-art methods.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 9","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148615695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Context-Aware Fragrance Discovery: Balancing Semantic Alignment and Catalogue Coverage Through Stochastic Ranking 上下文感知香味发现：通过随机排序平衡语义对齐和目录覆盖

IF 3.4 4区计算机科学

Expert Systems Pub Date : 2026-07-20 DOI: 10.1111/exsy.70369

Elena-Ruxandra Luţan, Costin Bădică

{"title":"Context-Aware Fragrance Discovery: Balancing Semantic Alignment and Catalogue Coverage Through Stochastic Ranking","authors":"Elena-Ruxandra Luţan, Costin Bădică","doi":"10.1111/exsy.70369","DOIUrl":"https://doi.org/10.1111/exsy.70369","url":null,"abstract":"<div>\u0000 \u0000 <p>In this paper, we propose a context-aware fragrance recommendation model, which moves the task beyond static similar scent matching towards situational recommendation, where different perfumes are appropriate for different social environments. In our formulation, a perfume collection is modelled as a dynamic olfactory wardrobe, where each perfume is tailored to specific environmental and social demands. We formalize each perfume through a unified representation which combines contextual suitability and affective signals extracted from user reviews, together with olfactory catalogue data. The proposed model integrates deterministic top-k ranking and stochastic candidate selection to balance relevance and exploration. We assess the performance of the model with complementary evaluation measures covering identity retrieval, ranking quality of success hits, semantic utility and catalogue exploration. The results indicate that while even simple popularity baselines remain highly competitive in raw retrieval precision, our fused context-affective model provides stronger contextual utility than single-feature strategies. Furthermore, our stochastic ranking variant substantially improves catalogue coverage with only a limited loss in retrieval quality.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 9","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148534149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning a Semantic Similarity Orthogonal Space for Model-Level AI-Generated Image Source Attribution 基于模型级人工智能图像源归属的语义相似正交空间学习

IF 3.4 4区计算机科学

Expert Systems Pub Date : 2026-07-17 DOI: 10.1111/exsy.70359

Yuchu Lin, Xinqi Jiang, Wei Wang, Jinyu Tian

{"title":"Learning a Semantic Similarity Orthogonal Space for Model-Level AI-Generated Image Source Attribution","authors":"Yuchu Lin, Xinqi Jiang, Wei Wang, Jinyu Tian","doi":"10.1111/exsy.70359","DOIUrl":"https://doi.org/10.1111/exsy.70359","url":null,"abstract":"<div>\u0000 \u0000 <p>The rapid evolution of diffusion models has established artificial intelligence generated image (AIGI) as a dominant paradigm in digital media, simultaneously escalating the risks of deepfakes and copyright infringement. While existing forensic methods focus primarily on distinguishing real from synthetic content, they fail to address the critical attribution challenge: identifying the specific model architecture responsible for a generated image. To bridge this gap, this paper proposes a novel AIGI source tracing framework capable of pinpointing source models in black-box scenarios. Our approach is grounded in the hypothesis that images generated by the same model under identical semantic conditions exhibit consistent stylistic signatures and detail-level artefacts. The framework operates through a ‘reconstruct-and-compare’ paradigm. First, we employ a CLIP-based optimization algorithm to reconstruct the semantic prompt of the query image, enabling the generation of a reference sample from the candidate model. Second, to accurately measure the provenance similarity between the query and the reference, we introduce a Semantic Comparison Network based on Orthogonal Extension. This network utilizes a feature purification mechanism to decouple shared semantic content from model-specific visual attributes. Furthermore, it employs a multi-stage orthogonal training strategy to extract mutually independent feature subspaces, ensuring a comprehensive capture of diverse stylistic dimensions. Experimental results demonstrate that this framework effectively overcomes the limitations of current classifier-based attribution, offering a robust solution for digital forensics and accountable AI governance.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 9","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148533529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0