Focus! Relevant and Sufficient Context Selection for News Image Captioning
Mingyang Zhou, Grace Luo, Anna Rohrbach, Yu Zhou · 2022
News Image Captioning requires describing an image by leveraging additional context from a news article.Previous works only coarsely leverage the article to extract the necessary context, which makes it challenging for models to identify relevant events and named entities.In our paper, we first demonstrate that by combining more fine-grained context that captures the key named entities (obtained via an oracle) and the global context that summarizes the news, we can dramatically improve the model's ability to generate accurate news captions.This begs the question, how to automatically extract such key entities from an image?We propose to use the pre-trained vision and language retrieval model CLIP to localize the visually grounded entities in the news article and then capture the non-visual entities via an open relation extraction model.Our experiments demonstrate that by simply selecting a better context from the article, we can significantly improve the performance of existing models and achieve new state-of-the-art performance on multiple benchmarks. Serena Williams and Andy Murray in Wimbledon Mixed Doubles: It's HappeningCaption: Andy Murray practicing at the All England Club on Tuesday.He and Serena Williams have agreed to play together in Wimbledon's mixed doubles.WIMBLEDON, England -After days of copy remarks about the possibility, it has been confirmed that Andy Murray and Serena Williams will be a team in the mixed doubles event at Wimbledon.The two will sign in for the 48-team competition ahead of the 11 a.m.deadline on Wednesday morning, Matt Gentry, a spokesman for Murray, said on Tuesday.Murray, 32, is playing his third tournament since hip replacement surgery in January, and he is focusing on doubles to ease into his comeback.