Complex & Intelligent Systems最新文献

{"title":"Interpretable discovery of anisotropic dissipation limiters for hypersonic flows via flow-aligned spatiotemporal graph attention and symbolic distillation","authors":"Zechen Wang, XiaoLi Huang, Yalong Gou, Yuyang Wang, Jiayu Liu, Rong Luo, YiLin Wang, Yin Long","doi":"10.1007/s40747-026-02468-0","DOIUrl":"https://doi.org/10.1007/s40747-026-02468-0","url":null,"abstract":"","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"1 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148842896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Neuron image segmentation algorithm based on dual encoder and Hadamard product","authors":"Huiling Feng, Rongqin Wu, Shengwen Chen, Jieyuan Hu, Junyu Zhang, Fuyun He","doi":"10.1007/s40747-026-02395-0","DOIUrl":"https://doi.org/10.1007/s40747-026-02395-0","url":null,"abstract":"","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"22 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"$$hbox {D}^2$$RSM-former: a directional deformable refinement transformer with soft-edge smooth span mask for robust handwritten text recognition","authors":"Yao Wei, Haicheng Qu, Jiandong Li","doi":"10.1007/s40747-026-02477-z","DOIUrl":"https://doi.org/10.1007/s40747-026-02477-z","url":null,"abstract":"Handwritten text recognition technology plays a crucial role in historical document digitization, archive management systems, and cultural heritage preservation. Although existing methods based on Convolutional Neural Networks and Vision Transformers have achieved remarkable progress in feature extraction and global modeling, they still exhibit limitations when addressing inherent challenges of handwritten text, including stroke deformation, character adhesion, and cross-lingual robustness. To address these challenges, we propose a Directional Deformable Refinement Transformer with Soft-edge Smooth Span Mask for Robust Handwritten Text Recognition ( <jats:inline-formula> <jats:alternatives> <jats:tex-math>$$hbox {D}^2$$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:msup> <mml:mtext>D</mml:mtext> <mml:mn>2</mml:mn> </mml:msup> </mml:math> </jats:alternatives> </jats:inline-formula> RSM-Former), which innovatively integrates a Hierarchical Adaptive Directional Deformable Feature Extractor (HADD-FE), a Soft-edge Smooth Span Mask (SSSM) strategy, and a Heterogeneous Interactive Refinement Encoder (HIREncoder). HADD-FE dynamically adjusts receptive field configurations through an adaptive directional deformable mechanism, effectively capturing anisotropic features of handwritten text. The SSSM enhances generalization through smooth boundary transitions and adaptive length sampling. HIREncoder achieves synergistic modeling of local–global features through dialogic head contextual attention and heterogeneous iterative refinement mechanisms. Extensive experiments on six benchmark datasets demonstrate that, without relying on any pre-training or synthetic data, <jats:inline-formula> <jats:alternatives> <jats:tex-math>$$hbox {D}^2$$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:msup> <mml:mtext>D</mml:mtext> <mml:mn>2</mml:mn> </mml:msup> </mml:math> </jats:alternatives> </jats:inline-formula> RSM-Former achieves state-of-the-art performance on READ2016, LAM, and IAM datasets, while also demonstrating highly competitive results on RIMES2011, BRESSAY, and VOHTR2018 datasets.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"132 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Social media rumor detection using multi-relational temporal-semantic augmented dynamic graph neural networks","authors":"Ailin Li, Jizong Wang, Zhihang Wang, Wendi Zhu, Wei Sheng, Fuyuan Chen","doi":"10.1007/s40747-026-02463-5","DOIUrl":"https://doi.org/10.1007/s40747-026-02463-5","url":null,"abstract":"","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"44 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 dual-branch multi-scale network for thyroid nodule ultrasound image segmentation","authors":"Hao Chen, Qiong Zhang, Zhe Wang, Xu Wu, Yuwei Yang","doi":"10.1007/s40747-026-02484-0","DOIUrl":"https://doi.org/10.1007/s40747-026-02484-0","url":null,"abstract":"","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"7 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Convergence and diversity cooperative-based coevolutionary algorithm for many-objective optimization","authors":"Wei Li, Weize Qin, Ning Yang, Qing Xu, Ying Huang","doi":"10.1007/s40747-026-02466-2","DOIUrl":"https://doi.org/10.1007/s40747-026-02466-2","url":null,"abstract":"","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"9 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Multi-view feature fusion and contrastive representation learning for pipeline leak detection","authors":"Xuemei Meng","doi":"10.1007/s40747-026-02404-2","DOIUrl":"https://doi.org/10.1007/s40747-026-02404-2","url":null,"abstract":"","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"49 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Multi-level visual-language models feature learning for generalizable anomaly detection","authors":"jianfeng Qiu,junfa Li,Juan Xie,Xueliang Ma,Ke Xu","doi":"10.1007/s40747-026-02462-6","DOIUrl":"https://doi.org/10.1007/s40747-026-02462-6","url":null,"abstract":"Abstract Zero-shot anomaly detection (ZSAD) aims to identify anomalies in target datasets without accessing their samples. Although CLIP and other large-scale vision language models show strong generalization, their potential for multi-level feature extraction in ZSAD remains underexplored. To address this, we propose a Multi-Level Feature Learning (MLFL) framework to enhance the zero-shot capability of CLIP via hierarchical alignment. MLFL adopts a two-stage training paradigm: Multi-Level Text Prompt Tuning (MLTP) and Multi-Level Text-Image Feature Alignment (MLFA). MLTP learns object-agnostic and object-aware prompts tailored to different encoder blocks. MLFA aligns textual and visual features using linear layers for shallow blocks and a Deep Feature Alignment (DFA) module for deep blocks. To compress parameters and preserve semantics, we introduce a Generalized Prompt Distillation (GPD) module that distills object-aware prompts into a unified representation. Experiments on seven industrial datasets achieve state-of-the-art performance, and deployment tests on edge devices demonstrate the potential applicability of the framework in practical industrial scenarios.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"51 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148896062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"MSSFFE-Net: a fine-grained object recognition network based on multi-scale spatial-frequency domain feature enhancement","authors":"Yimeng Wang, Jie Ren, Changming Sun, Arcot Sowmya, Changmiao Li, Weichuan Zhang","doi":"10.1007/s40747-026-02445-7","DOIUrl":"https://doi.org/10.1007/s40747-026-02445-7","url":null,"abstract":"","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"13 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148728765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Ont4RE, a computation framework for distant supervision and entity-property relation extraction in construction documents","authors":"Yuhang Wen, Junjie Jiang, Longhui Liao, Sui Pheng Low, Maxine Chan, Omar Castrejon-Campos, Olga Pilipenets, Chengke Wu","doi":"10.1007/s40747-026-02442-w","DOIUrl":"https://doi.org/10.1007/s40747-026-02442-w","url":null,"abstract":"","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"66 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148728766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}