Although the Mask region-based convolutional neural network (R-CNN) model possessed a dominant position for complex and variable road scene segmentation, some problems still existed, including insufficient feature expressive ability and low segmentation accuracy. To address these problems, a novel road scene segmentation algorithm based on the modified Mask R-CNN was proposed. The multi-scale backbone network, Res2Net, was utilized to replace the ResNet network, and aimed to improve the feature extraction capability. The soft non-maximum suppression algorithm with attenuation function (soft-NMS) was adopted to improve detection efficiency in the case of a higher overlap rate. The comparison analyses of partition accuracy for various models were performed on the adopted Cityscapes dataset. The results demonstrated that the modified Mask R-CNN effectively increased the segmentation accuracy, especially for small and highly overlapping objects. The adopted Res2Net and soft-NMS can effectively enhance the feature extraction and improve segmentation performance. The average accuracy of the modified Mask R-CNN model reached up to 0.321, and was 0.054 higher than Mask R-CNN. This work provides important guidance to design a more efficient road scene instance segmentation algorithm for further promoting the actual application in automatic driving systems.

Grain storage temperature prediction is crucial for silo safety and can effectively prevent mold and mildew caused by increasing grain temperature and condensation due to decreasing grain temperature. However, current prediction methods lead to information redundancy when capturing temporal and spatial dependencies, which diminishes prediction accuracy. To tackle this issue, this paper introduces an adaptive multi-scale feature fusion transformer model (AMSformer). Firstly, the model utilizes the adaptive channel attention (ACA) mechanism to adjust the weights of different channels according to the input data characteristics and suppress irrelevant or redundant channels. Secondly, AMSformer employs the multi-scale attention mechanism (MSA) to more accurately capture dependencies at different time scales. Finally, the ACA and MSA layers are integrated by a hierarchical encoder (HED) to efficiently utilize adaptive multi-scale information, enhancing prediction accuracy. In this study, actual grain temperature data and six publicly available datasets are used for validation and performance comparison with nine existing models. The results demonstrate that AMSformer outperforms in 36 out of the 58 test cases, highlighting its significant advantages in prediction accuracy and efficiency.

Neural Radiance Fields (NeRF) reconstruction faces significant challenges under non-ideal conditions, such as sparse viewpoints or missing camera pose information. Existing approaches frequently assume accurate camera poses and validate their effectiveness on standard datasets, which restricts their applicability in real-world scenarios. To tackle the challenge of sparse viewpoints and the inability of Structure-from-Motion (SfM) to accurately estimate camera poses, we propose a novel approach. Our method replaces SfM with the MASt3R-SfM algorithm to robustly compute camera poses and generate dense point clouds, which serve as depth–space constraints for NeRF reconstruction, mitigating geometric information loss caused by limited viewpoints. Additionally, we introduce a high-frequency annealing encoding strategy to prevent network overfitting and employ a depth loss function leveraging Pearson correlation coefficients to extract low-frequency information from images. Experimental results demonstrate that our approach achieves high-quality NeRF reconstruction under conditions of sparse viewpoints and missing camera poses while being better suited for real-world applications. Its effectiveness has been validated on the Real Forward-Facing dataset and in real-world scenarios.

Unstructured Chinese medical texts are rich sources of entity and relational information. The extraction of entity relationships from medical texts is pivotal for the construction of medical knowledge graphs and aiding healthcare professionals in making swift and informed decisions. However, the extraction of entity relationships from these texts presents a formidable challenge, notably due to the issue of overlapping entity relationships. This study introduces a novel extraction model that leverages RoFormer’s rotational position encoding (RoPE) technique for an efficient implementation of relative position encoding. This approach not only optimizes positional information utilization but also captures syntactic dependency information by constructing a weighted adjacency matrix. During the feature fusion phase, the model employs an entity attention mechanism for a deeper integration of features, effectively addressing the challenge of overlapping entity relationships. Experimental outcomes demonstrate that our model achieves an F1 score of 83.42 on datasets featuring overlapping entity relations, significantly outperforming other baseline models.

This paper presents a randomly overlapping dual-component radar signals recognition method based on a convolutional neural network-swin transformer (CNN-ST) under different signal-to-noise ratio (SNR), for improving the lower recognition performance and the higher computational costs of the conventional methods. To enhance the feature representation ability and decrease the loss of the detailed features of dual-component radar signals under different SNR, the swin transformer is adopted and integrated into the designed CNN model. An inverted residual structure and lightweight depthwise convolutions are used to maintain the powerful representational ability. The results show that the dual-component radar signals recognition accuracy of the proposed CNN-ST is up to 82.58% at -8 dB, which shows the better recognition performance of the CNN-ST over others. The dual-component radar signals recognition accuracies under different SNR are all more than 88%, which verified that the CNN-ST achieves better recognition accuracy under different SNR. The recognition performance of 2FSK-EQFM, 2FSK-LFM, 2FSK-NS, EQFM-LFM, EQFM-NS, and LFM-NS are up to 94.44%, 93.33%, 88.89%, 95.56%, 87.78%, and 94.44% at SNR of -8 dB, respectively. This work offers essential guidance in enhancing dual-component radar signals recognition under different SNR and promoting actual applications.

Under sample-size-limited conditions, the recognition accuracy of imperfect corn kernels is severely degraded. To address this issue, a recognition framework that integrates a Residual Generative Spatial–Channel Synergistic Attention Generative Adversarial Network (RGSGAN) with a Multi-Scale Asymmetric Convolutional Residual Network (MACRNet) was proposed. First, residual structures and a spatial–channel synergistic attention mechanism are incorporated into the RGSGAN generator, and the Wasserstein distance with gradient penalty is integrated to produce high-quality samples and expand the dataset. On this basis, the MACRNet employs a multi-branch asymmetric convolutional residual module to perform multi-scale feature fusion, thereby substantially enhancing its ability to capture subtle textural and local structural variations in imperfect corn kernels. The experimental results demonstrated that the proposed method attains a classification accuracy of 98.813%, surpassing ResNet18, EfficientNet-v2, ConvNeXt-T, and ConvNeXt-v2 by 8.3%, 6.16%, 3.01%, and 4.09%, respectively, and outperforms the model trained on the original dataset by 5.29%. These results confirm the superior performance of the proposed approach under sample-size-limited conditions, effectively alleviating the adverse impact of data scarcity on the recognition accuracy of imperfect corn kernels.