We present an image caption system that addresses new challenges of automatically describing images in the wild. The challenges include high quality caption quality with respect to human judgments, out-of-domain data handling, and low latency required in many applications. Built on top of a state-of-the-art framework, we developed a deep vision model that detects a broad range of visual concepts, an entity recognition model that identifies celebrities and landmarks, and a confidence model for the caption output. Experimental results show that our caption engine outperforms previous state-of-the-art systems significantly on both in-domain dataset (i.e. MS COCO) and out of-domain datasets.
@article{arxiv.1603.09016,
title = {Rich Image Captioning in the Wild},
author = {Kenneth Tran and Xiaodong He and Lei Zhang and Jian Sun and Cornelia Carapcea and Chris Thrasher and Chris Buehler and Chris Sienkiewicz},
journal= {arXiv preprint arXiv:1603.09016},
year = {2016}
}