Camouflaged Object Detection (COD) is challenging due to the strong similarity between camouflaged objects and their surroundings, which complicates identification. Existing methods mainly rely on spatial local features, failing to capture global information, while Transformers increase computational costs.To address this, the Frequency-Assisted Mamba-Like Linear Attention Network (FMNet) is proposed, which leverages frequency-domain learning to efficiently capture global features and mitigate ambiguity between objects and the background. FMNet introduces the Multi-Scale Frequency-Assisted Mamba-Like Linear Attention (MFM) module, integrating frequency and spatial features through a multi-scale structure to handle scale variations while reducing computational complexity. Additionally, the Pyramidal Frequency Attention Extraction (PFAE) module and the Frequency Reverse Decoder (FRD) enhance semantics and reconstruct features. Experimental results demonstrate that FMNet outperforms existing methods on multiple COD datasets, showcasing its advantages in both performance and efficiency. Code available at https://anonymous.4open.science/r/FMNet-3CE5.

The quality of metal surfaces is critical in various industrial applications, including aerospace, manufacturing, and container transportation. Surface defects, such as cracks, dents, and scratches, not only compromise the structural integrity and aesthetics of metal products but also lead to significant economic losses if left undetected. As a result, the accurate and efficient detection of metal surface defects has become an essential task in industrial quality control. In recent years, the adoption of deep learning techniques has significantly advanced the performance of defect detection systems [1]. Convolutional neural networks (CNNs) and transformer-based models have demonstrated exceptional capabilities in handling complex image-based tasks, enabling automated and reliable defect detection. However, several challenges remain: 1) Metal defect often exhibits varied and localized features, making effective multi-scale feature aggregation vital for improving detection accuracy.

Incorrect boundary division, complex semantic representation, and differences in pronunciation and meaning often lead to errors in Chinese Named Entity Recognition(CNER). To address these issues, this paper proposes HREB-CRF framework: Hierarchical Reduced-bias EMA with CRF. The proposed method amplifies word boundaries and pools long text gradients through exponentially fixed-bias weighted average of local and global hierarchical attention. Experimental results on the MSRA, Resume, and Weibo datasets show excellent in F1, outperforming the baseline model by 1.1\%, 1.6\%, and 9.8\%. The significant improvement in F1 shows evidences of strong effectiveness and robustness of approach in CNER tasks.