Image-Text Surgery: Efficient Concept Learning in Image Captioning by Generating Pseudopairs.

IEEE Transactions on Neural Networks and Learning Systems(2018)

引用 28|浏览26
暂无评分
摘要
Image captioning aims to generate natural language sentences to describe the salient parts of a given image. Although neural networks have recently achieved promising results, a key problem is that they can only describe concepts seen in the training image-sentence pairs. Efficient learning of novel concepts has thus been a topic of recent interest to alleviate the expensive manpower of labeling d...
更多
查看译文
关键词
Visualization,Knowledge based systems,Syntactics,Training,Neural networks,Semantics
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