RefineCap: Concept-Aware Refinement for Image Captioning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Pittsburgh（匹兹堡大学）
英文摘要：
Automatically translating images to texts involves image scene understanding and language modeling. In this paper, we propose a novel model, termed RefineCap, that refines the output vocabulary of the language decoder using decoder-guided visual semantics, and implicitly learns the mapping between visual tag words and images. The proposed Visual-Concept Refinement method can allow the generator to attend to semantic details in the image, thereby generating more semantically descriptive captions. Our model achieves superior performance on the MS-COCO dataset in comparison with previous visual-concept based models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
