%0 Conference Proceedings
%T Good News, Everyone! Context driven entity-aware captioning for news images
%A Ali Furkan Biten
%A Lluis Gomez
%A Marçal Rusiñol
%A Dimosthenis Karatzas
%B 32nd IEEE Conference on Computer Vision and Pattern Recognition
%D 2019
%F Ali Furkan Biten2019
%O DAG; 600.129; 600.135; 601.338; 600.121
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3289), last updated on Tue, 25 Jan 2022 10:49:16 +0100
%X Current image captioning systems perform at a merely descriptive level, essentially enumerating the objects in the scene and their relations. Humans, on the contrary, interpret images by integrating several sources of prior knowledge of the world. In this work, we aim to take a step closer to producing captions that offer a plausible interpretation of the scene, by integrating such contextual information into the captioning pipeline. For this we focus on the captioning of images used to illustrate news articles. We propose a novel captioning method that is able to leverage contextual information provided by the text of news articles associated with an image. Our model is able to selectively draw information from the article guided by visual cues, and to dynamically extend the output dictionary to out-of-vocabulary named entities that appear in the context source. Furthermore we introduce" GoodNews", the largest news image captioning dataset in the literature and demonstrate state-of-the-art results.
%U https://ieeexplore.ieee.org/document/8953244
%U http://refbase.cvc.uab.es/files/BGR2019.pdf
%U http://dx.doi.org/10.1109/CVPR.2019.01275
%P 12458-12467