Canonical Correlation Inference for Mapping Abstract Scenes to Text
AAAI Conference on Artificial Intelligence(2016)
摘要
We describe a technique for structured prediction, based on canonical correlation analysis. Our learning algorithm finds two projections for the input and the output spaces that aim at projecting a given input and its correct output into points close to each other. We demonstrate our technique on a language-vision problem, namely the problem of giving a textual description to an "abstract scene".
更多查看译文
关键词
Image Captioning,Topic Modeling,Visual Question Answering,Semantic Reasoning,Language Modeling
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要