Hao Li

Knowledge graphs organize real-world facts as structured triples and have become a fundamental resource for search engines, question answering, recommender systems, and knowledge-enhanced large language models. However, real-world knowledge graphs remain highly incomplete, which limits their downstream reasoning ability. Existing pre-trained language model-based knowledge graph completion methods provide strong textual semantic representations, but they usually model graph structure only as shallow auxiliary features and remain weak in distinguishing structurally similar entities and topology-near negative samples. To address this limitation, this paper proposes a Dual-Level Structural Context Collaborative Framework (DSC2F) for knowledge graph completion. At the instance level, the framework introduces Structural Neighborhood Context (SNC) to inject local neighborhood evidence into the language model input and Relation-Aware Attention (RAA) to condition structural aggregation on the current relation. At the batch level, it constructs topology-aware training batches with biased random walk with restart, so that in-batch negatives are locally related to positive samples and impose stronger structural discrimination pressure. Experiments on WN18RR, FB15k-237, and Wikidata5M show that DSC2F achieves the best mean reciprocal rank and Hits@1 on all three datasets, consistently outperforming strong embedding-based and pre-trained language model-based baselines. Ablation studies and structural configuration analyses further verify that SNC, RAA, and Batch-Level Structural Context provide complementary benefits. These results demonstrate that collaborative modeling of instance-level and batch-level structural context can effectively enhance structure-aware entity representation and improve fine-grained entity prediction.

Image fusion technology aims to generate a more informative single image by integrating complementary information from multi-modal images. Despite the significant progress of deep learning-based fusion methods, existing algorithms are often limited to single or dual-dimensional feature interactions, thus struggling to fully exploit the profound complementarity between multi-modal images. To address this, this paper proposes a parallel multi-dimensional complementary fusion network, termed PMCFusion, for the task of infrared and visible image fusion. The core of this method is its unique parallel three-branch fusion module, PTFM, which pioneers the parallel synergistic perception and efficient integration of three distinct dimensions: spatial uncorrelation, channel-wise disparity, and frequency-domain complementarity. Leveraging meticulously designed cross-dimensional attention interactions, PTFM can selectively enhance multi-dimensional features to achieve deep complementarity. Furthermore, to enhance the detail clarity and structural integrity of the fused image, we have designed a dedicated multi-scale high-frequency detail enhancement module, HFDEM. It effectively improves the clarity of the fused image by actively extracting, enhancing, and injecting high-frequency components in a residual manner. The overall model employs a multi-scale architecture and is constrained by corresponding loss functions to ensure efficient and robust fusion across different resolutions. Extensive experimental results demonstrate that the proposed method significantly outperforms current state-of-the-art fusion algorithms in both subjective visual effects and objective evaluation metrics.

Vehicle re-identification (Re-ID) is a critical task in the fields of intelligent transportation and urban surveillance. This task faces numerous challenges, such as significant changes in shooting angles, strong similarities in appearance between different vehicles of the same model, and difficulties in modeling fine-grained differences. To overcome the shortcomings of existing methods in local feature extraction and multi-scale fusion, this paper proposes an attention-guided dual-branch feature fusion network (DAFF-Net). The network uses ResNet50-ibn as its backbone and designs two complementary feature extraction branches. One branch fuses cross-layer attention between shallow and deep features, introducing a Temperature-Calibration Attention Fusion Module (TCAF) to improve the accuracy of cross-layer feature fusion effectively. The other branch enhances multi-scale attention for mid-layer features, constructing a Multi-Scale Gated Attention Module (MSGA) to extract local details and directional structural information. Finally, the discriminative ability of the enhanced features is improved by concatenating the two branch features and jointly optimizing the network using triplet loss, cross-entropy loss, and center loss. Experimental results on the VeRi-776 and VehicleID public datasets indicate that the proposed DAFF-Net outperforms existing mainstream methods in multiple key metrics. On the VeRi-776 dataset, mAP and CMC@1 increased to 82.2% and 97.5%, respectively. In the three test subsets of the VehicleID dataset, the CMC@1 metric achieved 90.7%, 84.6%, and 82.1%, respectively, demonstrating the effectiveness of the proposed network in vehicle re-identification tasks.

As a key technology in multimodal information processing, infrared and visible image fusion holds significant application value in fields such as military reconnaissance, intelligent security, and autonomous driving. To address the limitations of existing methods, this paper proposes the Hierarchical Triple-Feature Interaction Fusion Network (TFI-Fusion). Based on a hierarchical triple-stream feature interaction mechanism, the network achieves high-quality fusion through a two-stage, separate-model processing approach: In the first stage, a single model extracts low-rank components (representing global structural features) and sparse components (representing local detail features) from source images via the Low-Rank Sparse Decomposition (LSRSD) module, while capturing cross-modal shared features using the Shared Feature Extractor (SFE). In the second stage, another model performs fusion and reconstruction: it first enhances the complementarity between low-rank and sparse features through the innovatively introduced Bi-Feature Interaction (BFI) module, realizes multi-level feature fusion via the Triple-Feature Interaction (TFI) module, and finally generates fused images with rich scene representation through feature reconstruction. This separate-model design reduces memory usage and improves operational speed. Additionally, a multi-objective optimization function is designed based on the network’s characteristics. Experiments demonstrate that TFI-Fusion exhibits excellent fusion performance, effectively preserving image details and enhancing feature complementarity, thus providing reliable visual data support for downstream tasks.

In image analysis, high-precision semantic segmentation predominantly relies on supervised learning. Despite significant advancements driven by deep learning techniques, challenges such as class imbalance and dynamic performance evaluation persist. Traditional weighting methods, often based on pre-statistical class counting, tend to overemphasize certain classes while neglecting others, particularly rare sample categories. Approaches like focal loss and other rare-sample segmentation techniques introduce multiple hyperparameters that require manual tuning, leading to increased experimental costs due to their instability. This paper proposes a novel CAWASeg framework to address these limitations. Our approach leverages Grad-CAM technology to generate class activation maps, identifying key feature regions that the model focuses on during decision-making. We introduce a Comprehensive Segmentation Performance Score (CSPS) to dynamically evaluate model performance by converting these activation maps into pseudo mask and comparing them with Ground Truth. Additionally, we design two adaptive weights for each class: a Basic Weight (BW) and a Ratio Weight (RW), which the model adjusts during training based on real-time feedback. Extensive experiments on the COCO-Stuff, CityScapes, and ADE20k datasets demonstrate that our CAWASeg framework significantly improves segmentation performance for rare sample categories while enhancing overall segmentation accuracy. The proposed method offers a robust and efficient solution for addressing class imbalance in semantic segmentation tasks.

Efficient and effective path planning can significantly enhance the task execution capabilities of UAVs in complex environments. This paper proposes an improved sampling-based path planning algorithm, Bi-APF-RRT*, which integrates an Artificial Potential Field (APF) method with a newly introduced repulsive coefficient and incorporates dynamic step size adjustments. To further improve path planning performance, the algorithm introduces strategies such as dynamic goal biasing, target switching, and region-based adaptive sampling probability. The improved Bi-APF-RRT* algorithm effectively controls sampling direction and spatial distribution during the path search process, avoiding local optima and significantly improving the success rate and quality of path planning. To validate the performance of the algorithm, this paper conducts a comparative analysis of Bi-APF-RRT* against traditional RRT* in multiple simulation experiments. Quantitative results demonstrate that Bi-APF-RRT* achieves a 59.6% reduction in average computational time (from 5.97 s to 2.41 s), a 20.6% shorter path length (from 691.56 to 549.21), and a lower average path angle (reduced from 33.28° to 29.53°), while maintaining a 100% success rate compared to 95% for RRT*. Additionally, Bi-APF-RRT* reduces the average number of nodes in the search tree by 45.8% (from 381.17 to 206.5), showcasing stronger obstacle avoidance capabilities, faster convergence, and smoother path generation in complex 3D environments. The results highlight the algorithm’s robust adaptability and reliability in UAV path planning.