Rule-driven News Captioning

arXiv:2403.05101v1 Announce Type: new
Abstract: News captioning task aims to generate sentences by describing named entities or concrete events for an image with its news article. Existing methods have achieved remarkable results by relying on the large-scale pre-trained models, which primarily focus on the correlations between the input news content and the output predictions. However, the news captioning requires adhering to some fundamental rules of news reporting, such as accurately describing the individuals and actions associated with the event. In …

abstract article arxiv captioning concrete correlations cs.ai cs.cl events focus generate however image predictions pre-trained models results scale type