@inproceedings{4364bd7af42045ab9303fb972ca8e22c,
title = "SPICE: semantic propositional image caption evaluation",
abstract = "There is considerable interest in the task of automatically generating image captions. However, evaluation is challenging. Existing automatic evaluation metrics are primarily sensitive to n-gram overlap, which is neither necessary nor sufficient for the task of simulating human judgment. We hypothesize that semantic propositional content is an important component of human caption evaluation, and propose a new automated caption evaluation metric defined over scene graphs coined SPICE. Extensive evaluations across a range of models and datasets indicate that SPICE captures human judgments over model-generated captions better than other automatic metrics (e.g., system-level correlation of 0.88 with human judgments on the MS COCO dataset, versus 0.43 for CIDEr and 0.53 for METEOR). Furthermore, SPICE can answer questions such as which caption-generator best understands colors? and can caption-generators count?.",
author = "Peter Anderson and Basura Fernando and Mark Johnson and Stephen Gould",
year = "2016",
doi = "10.1007/978-3-319-46454-1_24",
language = "English",
isbn = "9783319464534",
volume = "Part V",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer, Springer Nature",
pages = "382--398",
editor = "Bastian Leibe and Jiri Matas and Nicu Sebe and Max Welling",
booktitle = "Computer Vision - 14th European Conference, ECCV 2016, Proceedings",
address = "United States",
note = "European Conference on Computer Vision (14th : 2016) ; Conference date: 11-10-2016 Through 14-10-2016",
}