RefineCap: Concept-Aware Refinement for Image Captioning

09/08/2021
by   Yekun Chai, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset