21 July 2021 in IEEE Internet of Things Journal
The development of Internet of Things systems (IoTs) and 5G technology has allowed image and text information to be collected and spread at an unprecedentedly high speed. To improve the data processing capabilities of IoTs, the semantic relations between images and text should be extracted efficiently and accurately. Therefore, to reduce the enormous semantic differences between images and text, existing methods introduce consensus knowledge graphs into image–text matching tasks. However, these methods result in noisy edges during the graph construction stage and overlook detailed knowledge extraction, leading to reduced performance in semantic matching. In this article, a two-layer heterogeneous knowledge graph network is proposed to solve the above problems. The proposed model incorporates category knowledge and local knowledge for improved data representation. Specifically, a category-based hierarchical knowledge graph is constructed to learn representations of knowledge concepts through a hierarchical correlation graph embedding (HCGE) module. Then, a globally guided local attention (GLA) module is used to extract fine-grained local knowledge. Finally, the similarity between the input image and text is calculated based on knowledge-fused features to complete the matching process. Extensive experiments show that the proposed model can learn more effective knowledge features to improve the efficacy of image–text matching in.
2 August 2011 in Assembly Automation
Purpose – Computer-aided fragmented cultural relics repair is an effective method instead of manual repair. The purpose of this paper is to provide a 3D digital patching system for computer-aided cultural relics repair through using the scanned 3D data of fragmented cultural relics. It includes processes and tools that can be effectively used for fragmented cultural relics repair. Design/methodology/approach – An automatic 3D digital patching for fragmented culture relics repair is designed. The framework includes a surface segmentation based on region dilation, feature extraction based on height-map, pair matching and multi-block matching. Findings – The paper finds that the proposed 3D data patching is an efficient method for fragmented cultural relics repair. Practical implications – Early and effective planning and implementation of computer-aided fragmented cultural relics repair can significantly improve the reliability and availability of fragmented cultural relics repair. Originality/value – The paper presents a uniform framework of 3D digital patching for fragmented cultural relics repair.