Information Fusion最新文献

{"title":"Generating vision-language navigation instructions incorporated fine-grained alignment annotations","authors":"Yibo Cui ,&nbsp;Liang Xie ,&nbsp;Yu Zhao ,&nbsp;Jiawei Sun ,&nbsp;Erwei Yin","doi":"10.1016/j.inffus.2025.104107","DOIUrl":"10.1016/j.inffus.2025.104107","url":null,"abstract":"<div><div>Vision-Language Navigation (VLN) enables intelligent agents to navigate environments by integrating visual perception and natural language instructions, yet faces significant challenges due to the scarcity of fine-grained cross-modal alignment annotations. Existing datasets primarily focus on global instruction-trajectory matching, neglecting sub-instruction-level and entity-level alignments critical for accurate navigation action decision-making. To address this limitation, we propose FCA-NIG, a generative framework that automatically constructs navigation instructions with dual-level fine-grained cross-modal annotations. In this framework, an augmented trajectory is first divided into sub-trajectories, which are then processed through GLIP-based landmark detection, crafted instruction construction, OFA-Speaker based R2R-like instruction generation, and CLIP-powered entity selection, generating sub-instruction-trajectory pairs with entity-landmark annotations. Finally, these sub-pairs are aggregated to form a complete instruction-trajectory pair. The framework generates the FCA-R2R dataset, the first large-scale augmentation dataset featuring precise sub-instruction-sub-trajectory and entity-landmark alignments. Extensive experiments demonstrate that training with FCA-R2R significantly improves the performance of multiple state-of-the-art VLN agents, including SF, EnvDrop, RecBERT, HAMT, DUET, and BEVBERT. Incorporating sub-instruction-trajectory alignment enhances agents’ state awareness and decision accuracy, while entity-landmark alignment further boosts navigation performance and generalization. These results highlight the effectiveness of FCA-NIG in generating high-quality, scalable training data without manual annotation, advancing fine-grained cross-modal learning in complex navigation tasks.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"130 ","pages":"Article 104107"},"PeriodicalIF":15.5,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145939775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Secure Tobit filtering for multi-rate nonlinear systems under multi-node random access protocol: A Paillier encryption-decryption mechanism","authors":"Shuo Yang ,&nbsp;Raquel Caballero-Águila ,&nbsp;Jun Hu ,&nbsp;Antonia Oya-Lechuga","doi":"10.1016/j.inffus.2026.104146","DOIUrl":"10.1016/j.inffus.2026.104146","url":null,"abstract":"<div><div>In this paper, the secure Tobit filtering (TF) problem is investigated for nonlinear systems subject to measurement censoring under a multi-node random access protocol (MNRAP). A multi-rate sampling framework is considered, which allows the system states and measurement outputs to operate with distinct sampling periods, thus reflecting practical engineering constraints. Furthermore, to mitigate data collisions and improve resource utilization, the MNRAP is adopted to regulate the transmission order of measurement signals over communication networks. In addition, to safeguard the communication confidentiality between the sensor node and the filter, the Paillier encryption-decryption mechanism is incorporated. This protects the transmitted information from being intercepted by unauthorized third parties. This paper concentrates on developing an innovative secure TF scheme that guarantees the existence of an upper bound (UB) on the filtering error second moment. Subsequently, the minimization of the obtained UB is carried out in the trace sense by designing a proper filter gain. Additionally, the uniform boundedness of the filtering error is verified in the mean-square sense by establishing a sufficient criterion. Finally, the efficacy and advantages of the proposed secure TF approach are demonstrated through a simulation example.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"130 ","pages":"Article 104146"},"PeriodicalIF":15.5,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145957307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Attention-driven contrastive learning for cross-modal hashing with prototypical separation","authors":"Zhipeng He ,&nbsp;Wenzhe Liu ,&nbsp;Lian Wu ,&nbsp;Jinrong Cui ,&nbsp;Jie Wen","doi":"10.1016/j.inffus.2025.104078","DOIUrl":"10.1016/j.inffus.2025.104078","url":null,"abstract":"<div><div>Effective retrieval and structuring of heterogeneous data have grown more difficult due to the exponential development of multimedia data. The surge in data volume emphasizes the importance of efficient cross-modal hashing techniques, known for their rapid retrieval speed and minimal storage requirements, which have garnered attention recently. However, existing unsupervised cross-modal hashing methods often fail to capture latent semantic structures and meaningful modality interactions, which limits their retrieval performance. To address these challenges, we propose Attention-driven Contrastive Learning for Cross-Modal Hashing via Prototypical Separation (ACoPSe). The method introduces a modality-aware fusion mechanism to enhance cross-modal feature interaction and a prototype alignment strategy that reduces heterogeneity at the cluster level by leveraging pseudo-labels derived from clustering. Extensive experiments demonstrate that our method achieves comparable performance to state-of-the-art approaches.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"130 ","pages":"Article 104078"},"PeriodicalIF":15.5,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data augmentation with attentional feature aggregation for node classification in GNNs","authors":"Guangquan Lu ,&nbsp;Shilong Lin ,&nbsp;Yuxuan Hu ,&nbsp;Debo Cheng ,&nbsp;Chen Li ,&nbsp;Shichao Zhang","doi":"10.1016/j.inffus.2025.104089","DOIUrl":"10.1016/j.inffus.2025.104089","url":null,"abstract":"<div><div>Graph Neural Networks (GNNs) have demonstrated remarkable success in classification tasks on graphs, including multimedia applications such as image recognition, video analysis, and recommendation systems. However, most GNNs methods assume that the category of samples is balanced, which contradicts real-world class distribution. In practice, imbalanced category distribution often causes GNNs to neglect minority-class nodes during training, which in turn negatively impacts overall classification performance. Existing methods still face key challenges, including insufficient feature learning and inadequate generation of node homogeneity. To tackle these challenges, we propose GraphAFA, a novel <strong><u>Graph</u></strong>-based method that utilizes <strong><u>A</u></strong>ttentional <strong><u>F</u></strong>eature <strong><u>A</u></strong>ggregation to generate a small number of synthetic class nodes, thereby promoting sample equilibrium. GraphAFA consists of two key components: attention-based feature extraction and neighbor-aware node aggregation. Firstly, GraphAFA constructs a feature space and utilizes an attention mechanism to extract node features, enabling effective learning higher-order relationships among nodes. Secondly, during the node generation process, GraphAFA aggregates information from neighboring nodes to capture shared features, ensuring the newly generated nodes are more homogeneous and reducing the risk of generating heterogeneous samples. Finally, GraphAFA connects edges to the newly generated nodes, integrating them into the graph for downstream classification. Comprehensive experiments on three benchmark datasets show that GraphAFA consistently outperforms state-of-the-art methods in class-imbalanced node classification.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"130 ","pages":"Article 104089"},"PeriodicalIF":15.5,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145822970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ChatAssistDesign: A language-interactive framework for iterative vector floorplan generation via conditional diffusion","authors":"Luping Li ,&nbsp;Xing Su ,&nbsp;Han Lin ,&nbsp;Haoying Han ,&nbsp;Chao Fan ,&nbsp;Zhao Zhang ,&nbsp;Hongzhe Yue","doi":"10.1016/j.inffus.2025.104091","DOIUrl":"10.1016/j.inffus.2025.104091","url":null,"abstract":"<div><div>Architectural design, a complex optimization process requiring iterative revisions by skilled architects, increasingly leverages computational tools. While deep generative models show promise in automating floorplan generation, two key limitations persist: (1) reliance on domain expertise, creating high technical barriers for non-experts, and (2) lack of iterative refinement capabilities, limiting post-generation adjustments. To address these challenges, we propose ChatAssistDesign, an interactive text-driven framework combining (1) Floorplan Designer, a large language model (LLM) agent guiding users through design workflows, and (2) ConDiffPlan, a vector-based conditional diffusion model for layout generation. Extensive experimental results demonstrate that our framework achieves significant improvements over state-of-the-art methods in terms of layout diversity, visual realism, text-to-layout alignment accuracy, and crucially, the ability to support iterative refinement while maintaining high robustness against constraint conflicts. By abstracting design complexity from user skill and enabling dynamic post hoc edits, our approach reduces entry barriers and improves integration with downstream tasks.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"130 ","pages":"Article 104091"},"PeriodicalIF":15.5,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145796207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Federated learning in oncology: Bridging artificial intelligence innovation and privacy protection","authors":"Xin Qi ,&nbsp;Tao Xu ,&nbsp;Chengrun Dang ,&nbsp;Zhuang Qi ,&nbsp;Lei Meng ,&nbsp;Han Yu","doi":"10.1016/j.inffus.2026.104154","DOIUrl":"10.1016/j.inffus.2026.104154","url":null,"abstract":"<div><div>Artificial intelligence (AI), including machine learning and deep learning models, is increasingly transforming oncology by providing powerful tools to analyze complex multidimensional data. However, developing reliable and generalizable models requires large-scale training datasets, which are often constrained by privacy regulations and the decentralized nature of medical data across institutions. Federated learning has recently emerged as a promising approach that enables collaborative model training across multiple sites without sharing raw data. This survey presents the fundamental principles and architectural frameworks of federated learning, highlighting its strengths in protecting data privacy, improving model robustness, and facilitating the integration of multi-omics and multi-modal datasets. Key applications in cancer detection, prognosis prediction, and treatment response prediction are discussed, underscoring its potential to support clinical decision-making. Moreover, the survey highlights major challenges in applying federated learning to oncology and outlines key directions to advance precision medicine, including the integration of multi-modal data, foundation models, causal reasoning, and continual learning. With ongoing technological advancements, federated learning holds great promise to bridge AI innovation and privacy protection in oncology.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"130 ","pages":"Article 104154"},"PeriodicalIF":15.5,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Shrinkage matters: evidence from accuracy-diversity trade-off in regression ensembles","authors":"Han Feng ,&nbsp;Pengyang Song ,&nbsp;Yinuo Ren ,&nbsp;Hanfeng Zhou ,&nbsp;Jue Wang","doi":"10.1016/j.inffus.2025.104073","DOIUrl":"10.1016/j.inffus.2025.104073","url":null,"abstract":"<div><div>Regression ensembles, a competitive machine learning technique, have gained popularity in recent years. Popular ensemble schemes have evolved from equal weights (EWs), which utilize simple averages, to optimal weights (OWs), which optimize weights by minimizing mean squared error (MSE). Extensive research has not only validated the robustness of EWs but also introduced the concept of shrinkage, shrinking OWs towards EWs. This paper tackles the ensemble challenge through diversity theory, where ensemble MSE is decomposed into two components: global error and global diversity. Within the decomposition framework, OWs typically minimize global error at the expense of reduced global diversity, while EWs tend to maximize global diversity but often ignore the accuracy. To address the accuracy-diversity trade-off, we derive an optimal shrinkage factor that manages to minimize the ensemble MSE. Simulation results reveal the mediation effect of shrinkage weights, and empirical experiments on six UCI datasets and Brent monthly future prices demonstrate the superiority of the proposed method, whose mechanism is further expounded through an in-depth analysis of the shrinkage components. Overall, our approach provides a novel perspective on the efficacy of shrinkage in regression ensembles.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"130 ","pages":"Article 104073"},"PeriodicalIF":15.5,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comprehensive benchmark of spatial encoding methods for tabular data with deep neural networks","authors":"Jiayun Liu ,&nbsp;Manuel Castillo-Cara ,&nbsp;Raúl García-Castro","doi":"10.1016/j.inffus.2025.104088","DOIUrl":"10.1016/j.inffus.2025.104088","url":null,"abstract":"<div><div>Despite the success of deep neural networks on perceptual data, their performance on tabular data remains limited, where traditional models still outperform them. A promising alternative is to transform tabular data into synthetic images, enabling the use of vision architectures such as Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). However, the literature lacks a large-scale, standardized benchmark evaluating these transformation techniques. This work presents the first comprehensive evaluation of nine spatial encoding methods across 24 diverse regression and classification datasets. We assess performance, scalability, and computational trade-offs under a unified framework with rigorous hyperparameter optimization. Our results reveal a performance landscape structured by data regimes, defined by sample size (<em>N</em>) and dimensionality (<em>d</em>), and show that the transformation method exerts a significantly stronger influence on predictive performance than the chosen vision architecture. In particular, REFINED emerges as the most robust transformation across tasks and datasets. Hybrid models (CNN+MLP, ViT+MLP) consistently reduce predictive variance, offering advantages especially in smaller datasets, yet play a secondary role. These findings suggest that transforming tabular data into synthetic images is a powerful, yet data-dependent, strategy. This benchmark provides clear guidance for researchers and practitioners, offering key insights into scalability, transformation behavior, and architectural interplay, establishing a comprehensive reference for future research on spatial encodings for tabular data.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"130 ","pages":"Article 104088"},"PeriodicalIF":15.5,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncertainty-aware multi-view evidence fusion for feature selection in brain network analysis","authors":"Yuepeng Chen ,&nbsp;Weiping Ding ,&nbsp;Shangce Gao ,&nbsp;Jiaru Yang ,&nbsp;Tianyi Zhou ,&nbsp;Qichong Hua ,&nbsp;Fan Fu","doi":"10.1016/j.inffus.2025.104083","DOIUrl":"10.1016/j.inffus.2025.104083","url":null,"abstract":"<div><div>Accurate diagnosis of schizophrenia remains challenging due to the lack of reliable biomarkers. Dynamic functional connectivity (dFC) derived from resting-state fMRI provides a powerful representation of temporal brain dynamics; however, its inherently multi-view structure introduces severe challenges, including high dimensionality, heterogeneity across views, and uncertainty caused by preprocessing. Such uncertainty directly affects feature selection because unreliable features may degrade both diagnostic accuracy and interpretability. However, most existing feature selection methods fail to explicitly model and utilize uncertainty. To address these challenges, we propose a multi-view feature selection method based on evidence theory that explicitly models uncertainty while capturing inter-view consistency and complementarity. This approach enables the selection of both shared and view-specific discriminative patterns that are often overlooked in dynamic brain network analysis. We further introduce an information-theoretic consistency constraint to extract reliable shared information and an uncertainty-weighted loss based on the Dirichlet distribution to prioritize complementary features with lower uncertainty. By integrating confidence measures across views through evidence fusion, our method effectively quantifies and leverages uncertainty to optimize feature selection. Extensive experiments on three independent rs-fMRI schizophrenia datasets demonstrate improved classification accuracy and robustness, providing an interpretable and reliable tool for identifying biomarkers in neuropsychiatric research.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"130 ","pages":"Article 104083"},"PeriodicalIF":15.5,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bridging the sim-to-real gap in RF localization with large-scale synthetic pretraining","authors":"Armen Manukyan ,&nbsp;Rafayel Mkrtchyan ,&nbsp;Ararat Saribekyan ,&nbsp;Theofanis P. Raptis ,&nbsp;Hrant Khachatrian","doi":"10.1016/j.inffus.2025.104104","DOIUrl":"10.1016/j.inffus.2025.104104","url":null,"abstract":"<div><div>Radio frequency (RF) fingerprinting is a promising localization technique for GPS-denied environments, yet it tends to suffer from a fundamental limitation: Poor generalization to previously unmapped areas. Traditional methods such as <em>k</em>-nearest neighbors (<em>k</em>-NN) perform well where data is available but may fail on unseen streets, limiting real-world deployment. Deep learning (DL) offers potential remedies by learning spatial-RF patterns that generalize, but requires far more training data than what simple real-world measurement campaigns can provide. In this paper, we investigate whether synthetic data can bridge this generalization gap. Using (i) a real-world dataset from Rome and (ii) NVIDIA’s open-source ray-tracing simulator Sionna, we generate synthetic datasets under varying realism and scale conditions. Specifically, we use Dataset A containing real-world measurements with real base stations (BS) and real signals, and create Dataset B using real BS locations but simulated signals, Dataset C with both simulated BS locations and signals, and Dataset B’ which represents an optimized version of Dataset B where BS parameters are calibrated via Gaussian Process to maximize signal correlation with Dataset A. Our evaluation reveals a pronounced sim-to-real gap: Models achieving 25m error on synthetic data degrade to 184m on real data. Nonetheless, pretraining on synthetic data reduces real-world localization error from 323m to 162m; a 50% improvement over real-only training. Notably, simulation fidelity proves more important than scale: A smaller calibrated dataset (53K samples) outperforms a larger uncalibrated one (274K samples). To further evaluate the generalization capabilities of the models, we conduct experiments on an unseen geographical region using a real-world dataset from Oslo. In the zero-shot setting, the models achieve a root mean square error (RMSE) of 132.2m on the entire dataset, and 61.5m on unseen streets after fine-tuning on Oslo data. While challenges remain before meeting more practical localization accuracy, this work provides a systematic study in the field of wireless communication of synthetic-to-real transfer in RF localization and highlights the value of simulation-aware pretraining for generalizing DL models to real-world scenarios.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"130 ","pages":"Article 104104"},"PeriodicalIF":15.5,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145939825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}