Knowledge graph construction is aimed at storing and representing the knowledge of the objective world in a structured form. Existing methods for automatic construction of knowledge graphs have problems such as difficulty in understanding potential semantics and low precision. The emergence of Large Language Models (LLMs) provides an effective way for automatic knowledge graph construction. However, using LLMs as automatic knowledge graph construction engines relies on the embedding of schema layers, which brings challenges to the input length of LLMs. In this paper, we present a framework for Adaptive Construction of Knowledge Graph by leveraging the exceptional generation capabilities of LLMs and the latent relational semantic information of triples, named ACKG-LLM. Our proposed framework divides the knowledge graph construction task into three subtasks within a unified pipeline: triple extraction of open information, additional relational semantic information embedding and knowledge graph normalization based on schema-level embedding. The framework can construct knowledge graphs in different domains, making up for the defects of existing frameworks that need to retrain and fine-tune the internal model. Extensive experiments demonstrate that our proposed ACKG-LLM performs favorably against representative methods on the REBEL and WiKi-NRE datasets. The code is available athttps://github.com/KustTeamWQW/ACKG-LLM

In accomplishing the task of semantic segmentation of RGB-T remote sensing images, there is a great challenge due to severe occlusion, long-tailed data distribution, and insufficient pixel representation of certain objects. The effective use of high-level semantic contexts among various ground object categories is crucial, yet presents considerable diffi-culties. Traditional RGB-T remote sensing image semantic segmentation methods often fail to capture and utilize complex relationships and interdependencies among these categories, leading to reduced semantic segmentation accuracy. This paper proposes a novel, knowledge-enhancement module, empowering the model to utilize human-like commonsense knowledge. Specifically, we firstly employ the self-attention and cross-attention mechanisms to fuse RGB and Thermal features. Subsequently, we collect the weights of the classification layer to get a high-level semantic pool based on all the categories. Alongside this, a prior knowledge graph is developed to enable information propagation among all categories. We applied this knowledge-enhancement module to enhance the Mask R-CNN, named KEMask R-CNN. Experiments results on the RS RGB-T dataset demonstrate the progressiveness of the proposed method.

Although 5G and beyond communication technology empower a large number of edge heterogeneous devices and applications, the stringent security remains a major concern when dealing with the millions of edge computing tasks in the highly dynamic heterogeneous networks (HDHNs). Blockchains contribute significantly to addressing security challenges by guaranteeing the reliability of data and information. Since the node’s mobility, there are risks of exiting the network and leaving the remaining tasks noncomputed. Therefore, we model the cost function of offloaded computing tasks as a dynamic stochastic game. To reduce the computational complexity, the Time-Variant Mean-Field term (TVMF) is adopted to solve the cost-optimized problem. What’s more, we design an Adaptivity-Aware Practical byzantine fault tolerance consensus Protocol (AAPP) to dynamically formulate domains, execute leader node selection with regard to task completion and quickly verify computational results. In addition, a Dynamic Multi-domain Fractional Repetition uncoded repair storage (DMFR) scheme with variant redundancy is proposed to reduce the storage pressure and repair overhead. The simulation is implemented to demonstrate our scheme outperforms the benchmarks in terms of cost and time overhead.

Cross-scene multispectral point cloud classification aims to transfer knowledge of labeled source scenes to improve the discriminability of the model on the unlabeled target scenes. From a novel perspective, we argue that the information transfer between the source and target scenes can be used to solve cross-scene multispectral point cloud classification task. Specifically, we propose a Coupled Graph Convolutional Network (Coupled-GCN) to achieve joint alignment of node- and class-level structures within scenes by passing information between different scenes. To reduce the effect of spectral shift between the source and target scenes and seek scene-invariant intrinsic features, we propose a scene adaptive learning module by optimizing three different loss functions, namely, source classifier loss, domain classifier loss, and target classifier loss as a whole. In the cross-scene multispectral point cloud classification task, the proposed Coupled-GCN can alleviate the spectral shift problem compared to the traditional GCN and achieves an overall F_score of 65.04%.

Existing RGB-Infrared detection models do not explicitly encourage RGB and infrared to achieve effective multimodal learning. We find that when fusing RGB and infrared images, cross-modal redundant information weakens the degree of complementary information fusion. Inspired by this observation, we propose Redundant Information Suppression Network (RISNet) which suppresses cross-modal redundant information and facilitates the fusion of RGB-Infrared complementary information. Specifically, we design a novel mutual information minimization module to reduce the redundancy between appearance features from RGB images and infrared radiation features from infrared images, which enables the network to take full advantage of the complementary advantages of multimodality and improve the detection performance. Experimental results demonstrate that RISNet outperforms the best competitive algorithm for RGB-Infrared pedestrian detection.