Infrared Small Target Detection (IRSTD) requires strong target-level detection capability, which depends on effective modeling of long-range global dependencies. This demand has driven the transition from CNN-based approaches to Transformer-based architectures. Although Transformers improve global context modeling, their high computational cost limits practical deployment. Recent advances in Mamba enable efficient long-range dependency modeling with reduced complexity, offering a promising alternative that alleviates the efficiency limitations of Transformers while preserving target-level detection performance. However, Mamba is not inherently tailored for IRSTD, as it lacks explicit mechanisms for capturing fine-grained local details and modeling background variations across multiple spatial scales. To address these limitations, we propose MCFNet, an encoder-decoder framework that integrates Mamba to enhance target-level detection performance with moderate computational cost. MCFNet introduces a Detail-Capturable Convolution Block to strengthen local detail perception and a Multi-scale Contextual Mamba Block to improve background modeling across different scales. While the resulting dual-branch design enhances both global semantics and local details, it also introduces challenges in feature fusion. To this end, a Feature Fusion Decoding Module is further proposed to enable effective collaboration between global and local representations. Extensive experiments on multiple public IRSTD benchmark datasets demonstrate that MCFNet consistently outperforms existing methods in both pixel-level and target-level metrics, achieving higher detection accuracy with reduced false alarms. The code of our model is available at: https://github.com/Fihven/MCFNet.

Brain tumor segmentation from low-quality MRI scans poses significant challenges, particularly in sub-Saharan Africa, where the scans frequently suffer from low resolution and artifacts. Such degradations introduce substantial domain shifts that hinder the effectiveness of existing test-time adaptation (TTA) methods, largely due to catastrophic forgetting and the unreliability of pseudo-labels. In response, we introduce DRTTA, a dynamic and robust framework designed for effective test-time adaptation. This method maintains essential knowledge from the source domain by freezing certain parameters and utilizing adaptive BatchNorm, allowing for successful alignment with the target domain. During inference, DR-TTA employs a learnable augmentation strategy that is optimized to simulate distortions specific to the target domain. Additionally, a hybrid loss function incorporating geometric constraints is used to filter out unreliable pseudo-labels, thus stabilizing the training process. Our extensive experiments on the BraTS-SSA and BraTS-SIM datasets demonstrate that DR-TTA significantly surpasses existing state-of-the-art methods across key performance metrics. This advancement provides a viable solution for deploying brain tumor segmentation technology in real-world scenarios, particularly within resource-limited environments. Our source code is available at https://github.com/baiyou1234/DR-TTA.

Alzheimer’s Disease (AD) is a complex neurodegenerative disorder marked by memory loss, executive dysfunction, and personality changes. Early diagnosis is challenging due to subtle symptoms and varied presentations, often leading to misdiagnosis with traditional unimodal diagnostic methods due to their limited scope. This study introduces an advanced multimodal classification model that integrates clinical, cognitive, neuroimaging, and EEG data to enhance diagnostic accuracy. The model incorporates a feature tagger with a tabular data coding architecture and utilizes the TimesBlock module to capture intricate temporal patterns in Electroencephalograms (EEG) data. By employing Cross-modal Attention Aggregation module, the model effectively fuses Magnetic Resonance Imaging (MRI) spatial information with EEG temporal data, significantly improving the distinction between AD, Mild Cognitive Impairment, and Normal Cognition. Simultaneously, we have constructed the first AD classification dataset that includes three modalities: EEG, MRI, and tabular data. Our innovative approach aims to facilitate early diagnosis and intervention, potentially slowing the progression of AD. The source code and our private ADMC dataset are available at https://github.com/JustlfC03/MSTNet.

Recent research shows that data augmentation can mitigate data sparsity and improve the robustness of sequential recommendation. However, many augmentation strategies operate on raw sequences directly, easily disrupting the inherent semantic and temporal organization of user behaviors. To address this issue, we propose a Semantic-Aware Sequence Augmentor for recommendation that disentangles user sequences into stable (long-term) and spontaneous (short-term) latent factors, then selectively augments only the short-term component. This design preserves users’ primary semantic context while injecting controlled diversity into their short-term interests. Underlying our approach is a diffusion-based procedure that generates coherent augmented sequences without compromising semantic integrity. Extensive experiments on six real-world datasets confirm the effectiveness of SASA, showing clear improvements over conventional augmentation methods.

Accurate traffic flow forecasting is critical for the efficient operation of intelligent transportation systems (ITS), as it directly supports urban management and decision-making. With the increasing complexity of urban traffic, existing models often fail to fully capture the dynamic dependencies between traffic inflows and outflows. Some treat them as a unified process, while others only explore their commonalities. Inflows and outflows exhibit distinct patterns and interactions that require more refined modeling. To improve modeling performance, we propose BiSTGNN, a novel deep spatio-temporal network model which explicitly models bidirectional traffic flows as independent stochastic processes. Our approach leverages the unique temporal and spatial dependencies of each flow direction to distinguish transitions between directions, and integrates them through a composite graph convolution framework, offering a more detailed analysis of the transfer process between flows. Additionally, we introduce an innovative dynamic graph construction method that differentiates the interactions between inflows and outflows, capturing their heterogeneous relationships. Extensive experiments on five real-world traffic datasets demonstrate that our method outperforms state-of-the-art baselines, achieving superior accuracy in predicting both inflows and outflows.

Graph Convolutional Networks (GCNs) are currently the most widely used method for processing graph-structured data. However, recent research has revealed that the performance of GCNs dramatically decreases when confronted with adversarial attacks. This severely hinders their application in security-critical domains. Therefore, the development of GCNs that are resilient to adversarial attacks has emerged as a prominent research focus. Despite this, most current defense models with complex network architectures and optimization objectives are typically designed based on specific feature assumptions or attack manifestations, and do not enhance the inherent robustness of GCNs. They also overlook the changes induced by perturbations of varying intensities and the difference in attack phenomenon across different datasets. In response to this, we have delved into the impact of adversarial attacks on the spectrum, and propose an effective adaptive robust spectrum filter GCN (ASF-GCN). This approach enhances the robustness of GCN models through adaptive filtering without introducing additional conditional assumptions. We theoretically analyze that graphs have different robust frequency intervals under different conditions, validating the necessity of adaptive filtering. Additionally, we elucidate the role of degree distribution and maximum eigenvalue in adaptation. Extensive experiments on real-world graphs reveal that our model surpasses other defense models in overall performance.

The incidence and mortality rates of malignant tumors, such as acute leukemia, have risen significantly. Clinically, hospitals rely on cytological examination of peripheral blood and bone marrow smears to diagnose malignant tumors, with accurate blood cell counting being crucial. Existing automated methods face challenges such as low feature expression capability, poor interpretability, and redundant feature extraction when processing high-dimensional microimage data. We propose a novel fine-grained classification model, SCKansformer, for bone marrow blood cells, which addresses these challenges and enhances classification accuracy and efficiency. The model integrates the Kansformer Encoder, SCConv Encoder, and Global-Local Attention Encoder. The Kansformer Encoder replaces the traditional MLP layer with the KAN, improving nonlinear feature representation and interpretability. The SCConv Encoder, with its Spatial and Channel Reconstruction Units, enhances feature representation and reduces redundancy. The Global-Local Attention Encoder combines Multi-head Self-Attention with a Local Part module to capture both global and local features. We validated our model using the Bone Marrow Blood Cell Fine-Grained Classification Dataset (BMCD-FGCD), comprising over 10,000 samples and nearly 40 classifications, developed with a partner hospital. Comparative experiments on our private dataset, as well as the publicly available PBC and ALL-IDB datasets, demonstrate that SCKansformer outperforms both typical and advanced microcell classification methods across all datasets.

Long sequence time-series forecasting has important applications in long-term planning management scenarios. Researches based on Transformer effectively improve the capability for long sequence forecasting, but the quadratic computing complexity causes high resource consumption, limiting its application in long sequence scenarios. Meanwhile, many studies use the dot-product attention mechanism to model time dependency, but don't model the sequential information of time-series. It prevents the capture of more efficient long-term time dependencies. In addition, in the latest researches combining decomposition methods, there are the problem of trend information loss and the limitation of not being able to peel off more subdivided time patterns, which restrict the improvement of prediction ability. Therefore, we propose a Transformer-based model, Segformer. Firstly, Segformer extracts multiple components with obvious dependencies and coordinates the modeling process with the help of multi-component decomposition blocks and collaboration blocks. Secondly, SegAttention, a new variant of the attention mechanism with$O((\frac{L}{l})^{2})$computation complexity (whole sequence length L, segment length$l$), is proposed to model the dependencies between segments according to the values and orders in the segment sequences, and aggregate segment-level information. Experiments on five real datasets show that Segformer respectively reduces the forecasting error by about 13% and 22% compared with the two advanced benchmarks, and Segformer offers an efficient solution for long-term dependency modeling problem of time-series.

In the era of the Industrial Internet of Things, anomaly detection is important for real-world applications. However, most streaming data lack meaningful labels. Furthermore, some anomalies of streaming data may be concept drift, but few methods can deal with it. To address these challenges, we propose an unsupervised anomaly detection solution that can deal with streaming data, called OOA-UADS (Offline, Online, Analysis-an Unsupervised Anomaly Detection Solution for Multivariate Time Series). The solution consists of three stages: offline training, online prediction and anomaly analysis. Time convolutional networks and variational autoencoders are used to deconstruct and reconstruct the multivariate time series data to learn the normal patterns. The anomaly inversion mechanism identifies concept drift in the anomaly prediction stage by dynamically updating the classification thresholds. Intelligent anomaly analysis then provides anomaly dimensions to help engineers better analyse the anomalous behaviour. Our experiments show that OOA-UADS performs satisfactorily. On seven streaming datasets, OOA-UADS outperforms 11 baselines in terms of AUC and provides state-of-the-art F1 scores on three batch datasets.

Fine-grained visual categorization aims to learn a robust image representation modeling subtle differences from similar categories. Existing methods in this field tackle the problem by designing complex frameworks, which produce high-level features by performing first-order or second-order pooling. Despite the impressive performance achieved by these strategies, the single-order networks only carry linear or non-linear information of the last convolutional layer, neglecting the fact that features from different orders are mutually complementary. In this paper, we propose a multi-order feature statistical method (MOFS), which learns fine-grained features characterizing multiple orders. Specifically, the MOFS consists of two sub-modules: (i) a first-order module modeling both mid-level and high-level features. (ii) a covariance feature statistical module capturing high-order features. By deploying these two sub-modules on the top of existing backbone networks, MOFS simultaneously captures multi-level of discriminative patters including local, global and co-related patters. We evaluate the proposed method on three challenging benchmarks, namely CUB-200-2011, Stanford Cars, and FGVC-Aircraft. Compared with state-of-the-art methods, experiment results exhibit superior performance in recognizing fine-grained objects.

Coupled matrix-tensor factorization has been successfully applied in various fields in the processing of coupled data. However, the unshared components between coupled data tend to make the joint decomposition inaccurate. In order to solve this problem, in this work, we propose a method to improve the traditional method by combining individual decomposition and coupled decomposition to analyze the shared and unshared components. Numerical experiments are given to illustrate the advantages of the proposed method compared to the existing approaches.