Visually-Aware Context Modeling for News Image Captioning

arXiv:2308.08325v2 Announce Type: replace
Abstract: News Image Captioning aims to create captions from news articles and images, emphasizing the connection between textual context and visual elements. Recognizing the significance of human faces in news images and the face-name co-occurrence pattern in existing datasets, we propose a face-naming module for learning better name embeddings. Apart from names, which can be directly linked to an image area (faces), news image captions mostly contain context information that can only be found in the …

arxiv captioning context cs.cv image modeling type