The Core of Smart Cities: Knowledge Representation and Descriptive Framework Construction in Knowledge-Based Visual Question Answering

Visual question answering (VQA), which is an important presentation form of AI-complete task and visual Turing tests, coupled with its potential application value, attracted widespread attention from both researchers in computer vision natural language processing. However, there are no relevant research regarding the expression participation methods knowledge VQA. Considering importance for questions correctly, this paper analyzes researches stratification, process VQA proposes a description framework (KDF) to guide knowledge-based (Kb-VQA). The KDF consists basic theory, implementation specific applications. This focuses on describing mathematical models at theoretical levels, as well hierarchy theories key behaviors established basis. In our experiment, using statistics VQA’s accuracy literature, we propose good corroboration results forms paper.