@InProceedings{KhanhNguyen2023,
author="Khanh Nguyen
and Ali Furkan Biten
and Andres Mafla
and Lluis Gomez
and Dimosthenis Karatzas",
title="Show, Interpret and Tell: Entity-Aware Contextualised Image Captioning in Wikipedia",
booktitle="Proceedings of the 37th AAAI Conference on Artificial Intelligence",
year="2023",
volume="37",
number="2",
pages="1940--1948",
abstract="Humans exploit prior knowledge to describe images, and are able to adapt their explanation to specific contextual information given, even to the extent of inventing plausible explanations when contextual information and images do not match. In this work, we propose the novel task of captioning Wikipedia images by integrating contextual knowledge. Specifically, we produce models that jointly reason over Wikipedia articles, Wikimedia images and their associated descriptions to produce contextualized captions. The same Wikimedia image can be used to illustrate different articles, and the produced caption needs to be adapted to the specific context allowing us to explore the limits of the model to adjust captions to different contextual information. Dealing with out-of-dictionary words and Named Entities is a challenging task in this domain. To address this, we propose a pre-training objective, Masked Named Entity Modeling (MNEM), and show that this pretext task results to significantly improved models. Furthermore, we verify that a model pre-trained in Wikipedia generalizes well to News Captioning datasets. We further define two different test splits according to the difficulty of the captioning task. We offer insights on the role and the importance of each modality and highlight the limitations of our model.",
optnote="DAG",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3860), last updated on Wed, 17 Jan 2024 11:15:15 +0100",
opturl="https://doi.org/10.1609/aaai.v37i2.25285"
}