@inproceedings{f95c8544bddb4d7d97c918afc824874b,
title = "Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models",
abstract = "The Flickr30k dataset has become a standard benchmark for sentence-based image description. This paper presents Flickr30k Entities, which augments the 158k captions from Flickr30k with 244k coreference chains linking mentions of the same entities in images, as well as 276k manually annotated bounding boxes corresponding to each entity. Such annotation is essential for continued progress in automatic image description and grounded language understanding. We present experiments demonstrating the usefulness of our annotations for text-to-image reference resolution, or the task of localizing textual entity mentions in an image, and for bidirectional image-sentence retrieval. These experiments confirm that we can further improve the accuracy of state-of-the-art retrieval methods by training with explicit region-to-phrase correspondence, but at the same time, they show that accurately inferring this correspondence given an image and a caption remains really challenging.",
author = "Plummer, {Bryan A.} and Liwei Wang and Cervantes, {Chris M.} and Caicedo, {Juan C.} and Julia Hockenmaier and Svetlana Lazebnik",
note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 15th IEEE International Conference on Computer Vision, ICCV 2015 ; Conference date: 11-12-2015 Through 18-12-2015",
year = "2015",
month = feb,
day = "17",
doi = "10.1109/ICCV.2015.303",
language = "English (US)",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2641--2649",
booktitle = "2015 International Conference on Computer Vision, ICCV 2015",
address = "United States",
}