Object detection in aerial remote sensing images is essential for applications such as traffic management, public security, and ecological monitoring. However, existing methods struggle to handle multi-scale objects, complex backgrounds, and frequent occlusions, resulting in inadequate global feature extraction and unstable multi-scale loss calculations. To address these challenges, we propose the Multi-Feature Attention-Enhanced YOLO (MFAE-YOLO) network. Our approach introduces a Global Feature Fusion Processing (GFFP) module to enhance global feature extraction. The backbone network incorporates Fusion of Channel, Pixel, and Spatial (FCPS) attention modules to strengthen feature representation, while C2F-Feature Pool Extraction Units (C2F-FPEU) optimize pooling-based feature extraction. Additionally, we propose an Accurate IoU (AIoU) loss function to refine bounding box regression. Experiments on NWPU VHR-10, RSOD, and DIOR datasets demonstrate that MFAE-YOLO surpasses state-of-the-art methods, achieving mAP₅₀ values of 94.7%, 94.8%, and 67.0%, respectively. Ablation studies further validate the contributions of each module. The code is available at https://github.com/yiboCode/MFAE-YOLO.

Entity relation extraction mainly extracts relations from text, which is one of the important tasks of natural language processing. At present, some special fields have insufficient data; for example, agriculture, the metallurgical industry, etc. There is a lack of an effective model for entity relationship recognition under the condition of insufficient data. Inspired by this, we constructed a suitable small balanced data set and proposed a multi-neural network collaborative model (RBF, Roberta–Bidirectional Gated Recurrent Unit–Fully Connected). In addition, we also optimized the proposed model. This model uses the Roberta model as the coding layer, which is used to extract the word-level features of the text. This model uses BiGRU (Bidirectional Gated Recurrent Unit)–FC (Fully Connected) as the decoding layer, which is used to obtain the optimal relationship of the text. To further improve the effect, the input layer is optimized by feature fusion, and the learning rate is optimized by the cosine annealing algorithm. The experimental results show that, using the small balanced data set, the F1 value of the RBF model proposed in the paper is 25.9% higher than the traditional Word2vec–BiGRU–FC model. It is 18.6% higher than the recent Bert–BiLSTM (Bidirectional Long Short Term Memory)–FC model. The experimental results show that our model is effective.

As an important research field of artificial intelligence, knowledge graph develops rapidly, and triplet extraction is the key to the construction of a knowledge graph. The traditional pipeline extraction method will bring the error of entity recognition into the relationship extraction and affects the extraction effect. Besides, the traditional pipeline extraction method cannot solve the SEO (Single Entity Overlap) and EPO (Entity Pair Overlap) problems. Inspired by this, we compare the advantages and disadvantages of the mainstream methods of entity and relationship triples joint extraction, propose a new joint extraction method of entity relation triples based on a hierarchical cascade labeling model (named HCL model), and the HCL model is based on multi neural network cooperation. Further, we construct a balanced sampling Chinese dataset about the entity and relational triplet extraction which contains SEO and EPO. We carry out the experiments on the balanced data set, and the F1 value of the HCL model reaches 65.4% better than other baseline models.

Knowledge Question Answering is one of the important research directions in the field of robot intelligence. It is mainly based on background knowledge to analyze users’ questions and generate answers. It is one of the important application methods of knowledge graph technology. Compared with the traditional expert system of question and answer, it has the advantage of a large-scale background knowledge base and the traceability and interpretability of the question-answering process. Compared with the current ChatGPT (Chat Generative Pre-trained Transformer) technology, it has advantages in the proprietary segmentation field. Aiming at the problem of the accuracy of existing knowledge question-answering methods being low, this paper studies the method of semantic analysis for knowledge question-answering under the support of a knowledge database, proposes a knowledge question-answering method based on the superposition of multiple neural network models, and conducts experimental verification on the publicly available NLPCC2016KBQA(Knowledge Q&A Tasks in the 2016 Natural Language Processing and Chinese Computing Conference) data set. The experimental results show that the F1 value of this method is higher than that of the baseline model.

The object detection in high-resolution remote sensing images is affected by the uniqueness of imaging perspectives and the complexity of detection targets. Existing models face core challenges such as feature degradation of small objects, extreme scale variations, and intricate, dynamic backgrounds. To address these issues, this paper proposes a Triple Dynamic Optimization framework for remote sensing target detection (TDO-YOLO). First, construct the Deformable Reparameterized Feature Module (DRFM), which utilizes multi-branch feature fusion and structural reparameterization techniques to achieve refined capture of tiny and multi-scale targets. Second, we design an Adaptive Receptive Field Fusion Module (ARFF) that overcomes fixed receptive field limitations in traditional convolutions through parallel multi-scale kernel extraction and geometry-aware feature reorganization, significantly improving multi-scale object detection accuracy. Third, we propose a Convolutional Dynamic Position-Encoding Residual Attention Mechanism (CPERA), leveraging long-range dependency modeling and background suppression to effectively mitigate complex background interference and reduce false detection rates. Finally, we introduce a Multi-Scale Aware IoU (MSA-IoU) loss function specifically designed for remote sensing images, incorporating multi-scale perception mechanisms and dynamic weighting to enhance detection precision. Experimental results on the RSOD and DIOR datasets demonstrate that TDO-YOLO achieves mAP$_{50}$ scores of 96.6% and 68.7%, representing improvements of 3.87% and 3.15%, respectively, over the baseline model YOLOv11. Compared to current state-of-the-art networks, TDO-YOLO exhibits superior detection accuracy. The complete network model code is available at https://github.com/ChengXCode/TDO-YOLO.

Accurate road extraction from high-resolution remote sensing imagery is crucial for applications such as road network generation, urban planning, autonomous driving, and military operations. Although deep learning has significantly advanced segmentation performance, road extraction remains challenging because roads exhibit geometric and structural characteristics that differ markedly from general objects. We propose a local–global sparse transformer network (LGST-Net) that leverages sparse attention (SA) to capture both local details and global context. First, a coarse-to-fine feature-enhanced preprocessing (C2F-FEP) module extracts low-level features at a fine-grained scale during the model’s initial stage. Next, we design the LGST backbone, which comprises three novel components: local shift-mask SA (LSM-SA), global compressed sparse attention (GC-SA), and a spatial-channel gate. Extensive experiments on DeepGlobe and RoadTracer datasets demonstrate that LGST-Net outperforms state-of-the-art methods. Our code will be publicly available at https://github.com/JaymeWX/Road_LGST-Net