Multi-Modal Data Semantic Localization With Relationship Dependencies for Efficient Signal Processing in EH CRNs

Abstract

Due to spectrum scarcity and energy consumption caused by processing and transmitting multimodal data signals in cognitive radio networks (CRNs), locating key information in the signal for further energy management in EH CRNs is necessary. Therefore, to adaptively capture semantic associations of multimedia signals, we present a novel visual-semantic reasoning framework for phrases simultaneously localization. To address the preferences limitations of current algorithms caused by the independent localizing of phrases and the ignorance of inter-phrase dependencies, our framework models the phrases simultaneously followed by inter-phrase dependencies-based jointly localization. Specifically, the framework consists of two core modules, including spatial-semantic perception tensor factorization and visual-semantic relationship reasoning network which can be denoted as SSPTF and VSRN, respectively. That is, SSPTF integrates regions and phrases into a tensor so that tensor factorization can be used to capture a shared potential association for all phrases. Furthermore, based on the predefined phrases-semantic dependencies graph, VSRN explicitly exploits the conjunctions between phrases to refine the phrase-region matching scores from SSPTF to achieve jointly localization. By constructing it as an end-to-end training architecture, the strong performance of the framework over Flicker-Entities30K on accuracy and the state-of-the-art results on some categories demonstrate the effectiveness of the proposed unified framework.