Large ship targets in SAR images have characteristics such as large image proportions, rich features and large feature differences in a single target, etc. Existing multi-scale ship detection algorithms for SAR data employ multi-scale feature pyramids or anchor-free extractors to capture features from large ship targets. However, the significant feature variation due to the internal structure and reflection of ships makes it difficult for current extractors to provide a consistent feature description, often resulting in fragmented detection outcomes for ship targets. This paper decomposes the large ship detection problem into the detection of individual ship components (including tail, hull and head), proposing a novel component-based detection method for large ship targets in SAR images. The proposed method enhances the network's efficiency in feature propagation and aggregation across different layers using the Generalized Efficient Layer Aggregation Network (GELAN) structure. Following the feature extraction of GELAN, a multi-level Multi-Pooling Channel Attention (MPCA) is integrated to optimize the feature extraction structure in a hierarchical manner. The method also incorporates environmental features around the target to strengthen the association between different ship components. The detected ship components are connected using a topological relationship algorithm based on component structure, culminating in the generation of ship target detection results. Experiments on the large ship component model dataset constructed for this paper demonstrate significant improvements of the proposed algorithm over the pre-optimized YOLOv8. The experimental results demonstrate that our method achieves promising detection performance when compared to the current state-of-the-art YOLO series algorithms and multi-scale SAR ship detection algorithms. The algorithm also effectively avoided noticeable loss or false detection of small ship targets present in the dataset.

Many studies focusing on integrating reviews with ratings to improve recommendation performance have been quite successful. However, these works still face several shortcomings: (1) The importance of dynamically integrating review and interaction data features is typically ignored, yet treating these fusion features equally may lead to an incomplete understanding of user preferences. (2) Some forms of soft attention methods are adopted to model the local semantic information of words. As features thus captured may contain irrelevant information, the generated attention map is neither discriminatory nor detailed. In this paper, we propose a novel A daptive H ierarchical A ttention-enhanced G ated network integrating reviews for item recommendation , named AHAG. AHAG is a unified framework to capture the hidden intentions of users by adaptively incorporating reviews. Specifically, we design a gated network to dynamically fuse the extracted features and select the features that are most relevant to user preferences. To capture distinguishing fine-grained features, we introduce a hierarchical attention mechanism to learn important semantic information features and the dynamic interaction of these features. Besides, the high-order non-linear interaction of neural factorization machines is utilized to derive the rating prediction. Experiments on seven real-world datasets show that the proposed AHAG significantly outperforms state-of-the-art methods. Furthermore, the attention mechanism can highlight the relevant information in reviews to increase the interpretability of the recommendation task. Source codes are available in https://github.com/luojia527/AHAG .

Arbitrary-oriented object detection remains a pivotal research focus due to its practical significance and inherent challenges. Existing methods often extend frameworks and sampling strategies designed for horizontal object detectors, which struggle to handle the arbitrary orientations, high aspect ratios, and diverse scales of oriented objects. To overcome these limitations, we propose a novel and efficient method for arbitrary-oriented object detection. This approach dynamically assigns prediction layers by object pixel area, then leverages wavelet transform-based energy weighting for bottom-up sample reassignment, optimizing feature representation for oriented targets. In addition, a robust framework integrates heatmap keypoint prediction on feature maps of a quarter-sized image, along with sparse predictions on other scales. By querying small-object regions within deep feature maps, a progressive top-down feature fusion strategy further enhances the perception of fine-grained details. Extensive evaluations on four benchmark datasets demonstrate the method's substantial improvements in detection performance, establishing its potential for broader applications in oriented object detection.