RefCap: Image Captioning with Referent Objects Attributes

Abstract In recent years, significant progress has been made in visual-linguistic multi-modality research, leading to advancements in visual comprehension and its applications in computer vision tasks. One fundamental task in visual-linguistic understanding is image captioning, which involves generating human-understandable textual descriptions given an input image. This paper introduces an end-to-end referring expression image captioning model that incorporates supervision of interesting objects. Our model utilizes user-specified object keywords as a prefix to generate specific captions that are relevant to the target object. The model consists of three modules including: i) visual grounding, ii) referring object selection, and iii) image captioning modules. To evaluate its performance, we conducted experiments on the RefCOCO and COCO captioning datasets. The experimental results demonstrate that our proposed method effectively generates meaningful captions aligned with users' specific interests.