Injecting Prior Knowledge into Image Caption Generation

ECCV Workshops(2020)

引用 6|浏览46
暂无评分
摘要
Automatically generating natural language descriptions from an image is a challenging problem in artificial intelligence that requires a good understanding of the visual and textual signals and the correlations between them. The state-of-the-art methods in image captioning struggle to approach human level performance, especially when data is limited. In this paper, we propose to improve the performance of the state-of-the-art image captioning models by incorporating two sources of prior knowledge:(i) a conditional latent topic attention, that uses a set of latent topics as an anchor to generate highly probable words and,(ii) a regularization technique that exploits the inductive biases in syntactic and semantic structure of captions and improves the generalization of image captioning models. Our experiments validate that our method produces more human interpretable captions and also leads to significant improvements on the MSCOCO dataset in both the full and low data regimes.
更多
查看译文
关键词
prior knowledge,image
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