TY  - CONF
AU  - Ali Furkan Biten
AU  - Lluis Gomez
AU  - Marçal Rusiñol
AU  - Dimosthenis Karatzas
A2  - CVPR
PY  - 2019//
TI  - Good News, Everyone! Context driven entity-aware captioning for news images
BT  - 32nd IEEE Conference on Computer Vision and Pattern Recognition
SP  - 12458
EP  - 12467
N2  - 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.
UR  - https://ieeexplore.ieee.org/document/8953244
L1  - http://refbase.cvc.uab.es/files/BGR2019.pdf
UR  - http://dx.doi.org/10.1109/CVPR.2019.01275
N1  - DAG; 600.129; 600.135; 601.338; 600.121
ID  - Ali Furkan Biten2019
ER  -