CAAI Transactions on Intelligence Technology最新文献

{"title":"FMTNet: A Fourier-Mamba–Transformer Enhanced Network for Medical Image Segmentation","authors":"Shaoqiang Wang,&nbsp;Guiling Shi,&nbsp;Yuanyuan Zhang,&nbsp;Sibo Qiao,&nbsp;Yuchen Wang,&nbsp;Yifan Wang,&nbsp;Yawu Zhao,&nbsp;Xiaochun Cheng","doi":"10.1049/cit2.70141","DOIUrl":"https://doi.org/10.1049/cit2.70141","url":null,"abstract":"<p>Models based on U-shaped networks have achieved widespread success in the field of medical image segmentation, but their performance is generally limited by structural bottlenecks in the network. At this stage, feature maps experience a sharp decline in spatial resolution due to continuous downsampling, resulting in significant loss of critical boundaries and structural details. Additionally, the local receptive fields of convolutions limit the effective modelling of global context. To address this core issue, we propose a novel enhanced segmentation network called FMTNet. FMTNet fundamentally enhances the expressive power of deep features by integrating an innovative composite enhancement module at the bottleneck of the U-Net. This module consists of three synergistically working submodules: the Fourier spatial fusion module, which introduces a frequency-domain perspective to compensate for and reconstruct high-frequency structural information lost in the spatial domain; the hybrid mamba–transformer module, which efficiently captures cross-regional long-range dependencies to establish global context and the multi-scale context Aggregation module, which fuses features of different scales to adapt to objects of varying sizes. We conducted extensive experiments on multiple public multi-modal datasets, including colonoscopy polyps, dermatoscopy lesions, breast ultrasound and dental X-rays. The results demonstrate that FMTNet comprehensively outperforms SOTA methods across all key metrics, showcasing exceptional segmentation accuracy and generalisation capabilities. Our research study demonstrates that by synergistically enhancing deep features across three dimensions—frequency, global, and multi-scale—FMTNet provides a general and efficient solution to address the bottleneck issues of U-Net, significantly enhancing the accuracy and robustness of medical image segmentation. The source code and pre-trained weights are available at https://github.com/shiguiling0-has/FMTNet.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 3","pages":"798-815"},"PeriodicalIF":5.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70141","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148357989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

{"title":"A Semantic Segmentation Network for Colorectal Polyp Images With Progressive Fusion of Dual-Branch Features","authors":"Tianxu Yan,&nbsp;Jiabin Yu,&nbsp;Zheng Li,&nbsp;Liangyu Chen,&nbsp;Hongmei Mi,&nbsp;Luyang Chen,&nbsp;Wei Si,&nbsp;Dongping Zhang,&nbsp;Hui Lin","doi":"10.1049/cit2.70132","DOIUrl":"https://doi.org/10.1049/cit2.70132","url":null,"abstract":"<p>Accurate segmentation of colorectal polyps is essential for early colorectal cancer screening, yet remains challenging due to weak foreground–background contrast, disrupted boundaries caused by specular reflections and intestinal folds, and pronounced scale variation among polyps. These factors make it difficult for existing methods to jointly preserve fine boundary details and robust global semantic context. To address these task-specific challenges, we propose a Dual-branch Feature Progressive Fusion Network (DFPF-Net) for colorectal polyp segmentation. DFPF-Net adopts a dual-encoder architecture that integrates a CNN-based encoder for local and boundary-sensitive representation for global semantic modelling. A boundary-aware branch equipped with stacked Inversely Perceive Information Layers (IPILs) enhances ambiguous and fragmented contours, while the semantic branch incorporates Misalignment Fusion Modules (MFMs) and a Misaligned Single-layer Reinforcement Module (MSRM) to alleviate semantic misalignment and insufficient cross-scale interaction. Furthermore, a Perceptual Information Fusion Module (PIFM) enables effective semantic–boundary collaboration, and a Multi-level Residual Decoding Module (MRDM) progressively reconstructs structurally consistent segmentation outputs. Extensive experiments on multiple public colonoscopy datasets demonstrate that DFPF-Net achieves competitive and robust segmentation performance. In particular, on the challenging ETIS dataset, DFPF-Net attains 0.785 mDice and 0.704 mIoU, indicating its capability in handling complex structures and ambiguous boundaries in colorectal polyp segmentation.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 3","pages":"900-919"},"PeriodicalIF":5.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70132","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148358041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

{"title":"Video Super-Resolution via Effective Spatio-Temporal Alignment Network","authors":"Bin Guo,&nbsp;Xin Wang,&nbsp;Hao Wen,&nbsp;Yuhong Fu,&nbsp;Jinxing Li,&nbsp;Hui Ma,&nbsp;Haoqian Wang,&nbsp;Yong Xu","doi":"10.1049/cit2.70151","DOIUrl":"https://doi.org/10.1049/cit2.70151","url":null,"abstract":"<p>Extracting spatio-temporal cues from neighbouring frames is challenging in video super-resolution (VSR). Although deformable alignment-based VSR methods have shown promise in aligning neighbouring frames with the reference frame, most existing methods rely on one or a few traditional convolutions to estimate motion offsets for spatio-temporal alignment, restricting receptive field size and alignment accuracy. To address these limitations, we propose an effective spatio-temporal alignment network (ESTA-Net) for VSR. The core component of our method is the group convolution-based alignment module (GCBAM), which utilises cascaded group convolutions to learn offsets across both the original and downsampled resolutions. By employing group convolutions rather than traditional convolutions, GCBAM enables the deformable alignment to achieve a wider receptive field with lower computational cost, thereby improving the accuracy of offset estimation. Additionally, the bi-scale alignment strategy within GCBAM enhances robustness to complex and large-scale motions. Furthermore, we introduce an attention-based feature enhancement module (AFEM) to refine the aligned features, focusing on critical details to improve reconstruction quality. Extensive experiments on standard benchmarks show that our ESTA-Net achieves superior VSR performance against other advanced methods, while maintaining a good equilibrium between model size and performance.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 3","pages":"726-738"},"PeriodicalIF":5.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70151","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148358303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

{"title":"Diversified Composite Prompting to Enhance Generalisation of Vision-Language Models","authors":"Xiaoyong Mei,&nbsp;Chong Tang,&nbsp;Zhengqun Dai,&nbsp;Fudan Zheng,&nbsp;Kongwen Zhang,&nbsp;Tianyu Lin","doi":"10.1049/cit2.70143","DOIUrl":"https://doi.org/10.1049/cit2.70143","url":null,"abstract":"<p>In recent years, prompt learning has shown promise in transferring pretrained vision-language models (VLMs) to downstream tasks. However, existing methods face two challenges in improving generalisation: (1) When leveraging the collaborative effect of multimodal prompts, it is often assumed that text and visual modalities share the same prompt requirements, neglecting the distinct hierarchical processing of their encoders, leading to prompt imbalance; and (2) current methods exhibit limited adaptability when facing diverse distribution shift scenarios, including class distribution shifts and image content variations. To address these challenges, we propose a diversified composite prompt learning (DCPL) framework that integrates unified and specific prompts. Specifically, to alleviate multimodal prompt imbalance, we design a shared root multimodal prompting strategy, which employs a shared root prompt and an independent derivation mechanism to generate the derived multimodal prompt (DMP), enabling independent deep prompting while maintaining implicit synergy across modalities. Furthermore, we design a dual-branch dynamic adaptive prompting strategy that produces the derived class-specific prompt (DCP) and image-specific prompt (ISP), driven by inter-class relations and image-patch context, respectively, to enhance adaptability across different distribution shifts. Extensive experiments on base-to-novel, cross-dataset, domain generalisation and few-shot learning demonstrate that the DCPL achieves superior performance, validating its robustness and generalisation.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 3","pages":"935-950"},"PeriodicalIF":5.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70143","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148357948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

{"title":"AT-AER: Adversarial Training With Adaptive Example Reuse","authors":"Meng Hu,&nbsp;Yanting Guo,&nbsp;Ran Wang,&nbsp;Xizhao Wang,&nbsp;Rihao Li,&nbsp;Qin Wang","doi":"10.1049/cit2.70121","DOIUrl":"https://doi.org/10.1049/cit2.70121","url":null,"abstract":"<p>Adversarial training (AT) is widely regarded as a crucial defense method for deep neural networks against adversarial attacks. Most of the existing AT methods suffer from the problems of insufficient coverage of perturbation space and robust overfitting. In view of this, we propose an AT framework with adaptive example reuse (AT-AER) to help improve the adversarial robustness of deep models. In AT-AER, a new concept named 2nd-order adversarial example (AE) is proposed by adaptively filtering AEs generated during the historical training phase, which achieves sufficient coverage of diverse attack directions. Meanwhile, by analysing the fundamental causes of robust overfitting, we propose the strategies of wave descending learning rate (WDLR), cosine increasing weight decay (CIWD) and cosine increasing attack strength (CIAS) in collaboration with AT-AER to optimise models. In addition, the Stochastic Weight Averaging (SWA) technique is introduced to further improve the stability of training. Finally, experiments on three benchmark datasets show that AT-AER exhibits significant advantages in the face of strong adversarial attacks. Its adaptive mechanism effectively alleviates the phenomenon of robust overfitting where the performance difference between the best model and the last model is less than 1%. The study further reveals that using traditional weak attacks (e.g., FGSM) to evaluate the robustness of models may lead to a false sense of reliability, indicating the necessity of using strong attacks for robustness evaluation. This study provides a solution for AT that balances efficiency and performance.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 3","pages":"769-783"},"PeriodicalIF":5.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70121","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148358135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

{"title":"Robust Partial Multi-Label Learning Under Dual Noise via Joint Subspace Learning","authors":"Yuanjian Zhang,&nbsp;Zhanbo Fang,&nbsp;Tianna Zhao,&nbsp;Duoqian Miao,&nbsp;Witold Pedrycz","doi":"10.1049/cit2.70134","DOIUrl":"https://doi.org/10.1049/cit2.70134","url":null,"abstract":"<p>Partial Multi-label Learning (PML) deals with the ambiguity where each instance is annotated with a set of candidate labels, and only a subset of which is valid. While existing PML methods focus primarily on label disambiguation, they often rely on the assumption of a clean feature space. However, in real-world applications, data are frequently plagued by the co-existence of label noise and feature noise, referred to as the dual noise challenge. Consequently, model robustness degrades substantially. To address this, we propose a framework named Ranking-Consistent Correntropy-based subspace learning for Partial Multi-label Learning (RCC-PML). Unlike existing dual noise PML methods that operate in the input space, our work introduces a subspace learning framework, where robust representation and semantic ranking are jointly optimized to enforce cross-space consistency. Specifically, we leverage the Maximum Correntropy Criterion (MCC) to construct robust scatter matrices, effectively suppressing heavy-tailed feature noise. To tackle label ambiguity, a ranking-consistent constraint is introduced to encourage a reasonable margin between ground-truth and false-positive labels in the projected subspace. Furthermore, we incorporate dual-graph regularization to preserve both the local manifold structure via anchor embedding and global semantic consistency. Finally, <i>L</i>_2,1 -norm regularization is imposed on the projection matrix to perform adaptive feature selection. Extensive experiments on benchmark datasets demonstrate that the proposed method significantly outperforms state-of-the-art algorithms, particularly in heavy-tailed environments.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 3","pages":"754-768"},"PeriodicalIF":5.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70134","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148358247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

{"title":"Multiple Transformer-Based Models for Phase-Sensitive Masking-Based Single-Channel Speech Enhancement","authors":"Matin Pashaian,&nbsp;Sanaz Seyedin","doi":"10.1049/cit2.70146","DOIUrl":"https://doi.org/10.1049/cit2.70146","url":null,"abstract":"<p>Leveraging both global contextual dependencies and local temporal-spectral patterns can further enhance speech quality and intelligibility, motivating the integration of diverse neural network structures for improved mask estimation. Furthermore, due to the limitations of existing time-frequency phase-aware masks, a new constrained phase-sensitive mask is introduced and estimated using the proposed architectures. In this paper, we first propose a modified transformer model for constrained phase-sensitive ideal magnitude ratio mask (cPSIRM) estimation (TRF-cPSIRM) to incorporate both magnitude and phase information and improve speech enhancement quality. The transformer model can extract global information, whereas the convolutional neural network (CNN) and convolutional recurrent network (CRN) are effective in capturing local content. CNNs have feature extraction capability due to their convolutional layers, and CRNs benefit from the temporal modelling strength of LSTM recurrent layers, which is useful for enhancement. Therefore, in this paper, to exploit both transformer (TRF) and CNN/CRN capabilities, we propose the cascaded structures (models) of CNN and TRF layers (CNN-TRF-cPSIRM) and also TRF and CRN layers (TRF-CRN-cPSIRM) for cPSIRM estimation and, consequently, speech enhancement. The CNN is used for feature extraction in CNN-TRF-cPSIRM and CRN for enhancement in TRF-CRN-cPSIRM. Moreover, considering the harmonic property of speech in the frequency spectrum, we present the transposed transformer-based model (TTRF), in which the neighbourhood relationship between the different frequency sub-bands is used as a sequence in the model. Then, to model both the long-term and short-term dependencies, the cascaded model of TTRF (intra-transformer) and TRF (inter-transformer) is proposed for cPSIRM estimation (TTRF-TRF-cPSIRM). The experimental results show that among these transformer-based models, the CNN-TRF-cPSIRM has the best performance, achieving up to about 0.44 perceptual evaluation of speech quality (PESQ) improvement over the baseline and 1.5 over the noisy speech.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 3","pages":"667-680"},"PeriodicalIF":5.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70146","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148358050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

{"title":"AGPLO-Driven Optimisation for Accurate Segmentation of Papillary Thyroid Carcinoma in Medical Imaging","authors":"Jing Ruan,&nbsp;Xiaoxiao Chen,&nbsp;Hanbing Yao,&nbsp;Yujia Xu,&nbsp;Shiqi Xu,&nbsp;Shihao Zhao,&nbsp;Yulun Wu,&nbsp;Yingting Dai,&nbsp;Yubing Chen,&nbsp;Shuqing Ma,&nbsp;Qiongying Zhang,&nbsp;Ying Zhou,&nbsp;Ali Asghar Heidari,&nbsp;Huiling Chen,&nbsp;Yangping Shentu","doi":"10.1049/cit2.70130","DOIUrl":"https://doi.org/10.1049/cit2.70130","url":null,"abstract":"<p>Papillary Thyroid Carcinoma (PTC) is the most prevalent thyroid malignancy, and accurate lesion segmentation is essential for clinical diagnosis and treatment planning. Metaheuristic optimisation algorithms have been widely used in Multi-Threshold Image Segmentation (MTIS), but many existing methods suffer from an imbalance between global exploration and local exploitation. This study aims to develop a robust and well-balanced optimisation algorithm to improve the accuracy and stability of MTIS for PTC images. An Adaptive Guided Polar Lights Optimisation (AGPLO) algorithm is proposed, which incorporates an adaptive phase-shift operator, magnetic guiding convergence, and energy burst exploration mechanisms to dynamically regulate search behaviour. AGPLO was evaluated on the IEEE CEC2017 benchmark suite and applied to Rényi entropy-based MTIS for PTC image segmentation. Experimental results on benchmark functions demonstrate that AGPLO outperforms several original and advanced metaheuristic algorithms in terms of convergence accuracy, stability, and robustness. In PTC image segmentation experiments, AGPLO achieves superior PSNR, SSIM, and FSIM values, producing clearer lesion boundaries and preserving structural details more effectively than comparative methods. The proposed AGPLO provides an effective and reliable optimisation framework for MTIS and shows strong potential for intelligent medical image analysis applications.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 3","pages":"847-858"},"PeriodicalIF":5.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70130","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148358074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

{"title":"A Robust Visual Inertial Odometry SLAM Considering Robot Self Dynamics","authors":"Junyin Qiu,&nbsp;Hong Liu,&nbsp;Tianwei Zhang","doi":"10.1049/cit2.70145","DOIUrl":"https://doi.org/10.1049/cit2.70145","url":null,"abstract":"<p>In this paper, to deal with the dynamic SLAM problem, we investigate feature tracking and IMU preintegration in visual-inertial odometry (VIO) and design a robust SLAM framework that explicitly considers robot self-dynamics. We propose a self-dynamics and IMU-aided feature tracker to predict initial optical flow and an iterative refinement method that accounts for patch affine deformation and illumination changes, improving tracking accuracy and robustness. Furthermore, we introduce an SE₂(3)-based IMU preintegration that preserves state correlations and consistently encodes robot self-dynamics for subsequent optimisation. A VIO framework with preprocessing, optimisation and loop-closing threads is developed to validate the proposed self-dynamics–aware tracker and SE₂(3)-based preintegration. Experiments, including module tests and ablation studies, demonstrate improved feature tracking accuracy, IMU noise propagation and overall VIO performance when explicitly modelling robot self-dynamics.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 3","pages":"784-797"},"PeriodicalIF":5.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70145","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148358194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

{"title":"A Dynamic Correlation-Information-Fusion-Based Spatiotemporal Network for Traffic Flow Forecasting","authors":"Dawen Xia,&nbsp;Zhan Lin,&nbsp;Xingyan Wang,&nbsp;Ruixi Huang,&nbsp;Jinhui Hu,&nbsp;Yang Hu,&nbsp;Huaqing Li","doi":"10.1049/cit2.70142","DOIUrl":"https://doi.org/10.1049/cit2.70142","url":null,"abstract":"<p>Traffic Flow Forecasting (TFF) is a foundational task in the development of Intelligent Transport Systems (ITSs). The primary challenge is to undertake a comprehensive exploration of the intrinsic dynamic spatiotemporal correlations of the road network, unveiling the long-term evolutionary traffic trends. Furthermore, most existing methods often solely depend on the single traffic condition and neglect the enhancement of correlated features collected from traffic sensors in prediction. To this end, we propose a dynamic correlation-information-fusion-based (DCIF) spatiotemporal network for TFF, which models the spatiotemporal correlations of road networks, thereby effectively capturing dynamically changing characteristics. Specifically, a spatiotemporal feature enhancement (STFE) mechanism is employed to capture the directional and location-aware characteristics of traffic flow, thereby enhancing the representation of traffic flow and the capability of spatiotemporal feature extraction. Then, a gated attention unit (GAU) is constructed to meticulously extract the deep dynamic trends inherent within traffic data. Finally, a dynamic feature matrix (DFM) is formulated, incorporating spatial graph convolution to provide comprehensive semantic contextual information. The DFM captures the dynamic topology of the deeper feature network in real time by fusing spatial node information and traffic speed features as correlation information. Extensive experiments demonstrate that DCIF significantly outperforms other baselines in prediction accuracy, thereby further substantiating its validity and reliability in TFF.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"11 3","pages":"859-874"},"PeriodicalIF":5.1,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70142","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148358280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}