SPICE: Semantic Propositional Image Caption Evaluation
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Prior works have investigated the alignment between metrics and human judgment.
“Prior works have investigated the alignment between metrics and human judgment.23,33”
From Evaluating progress in automatic chest X-ray radiology report generation (2023) · cites this paper as [33]
The citation lists haven’t been fetched yet
References 45 · Cited by 1,986
- Authors
- Anderson, P., Fernando, B., Johnson, M., & Gould, S.
- Affiliations
- Australian National University (AU)
- Macquarie University (AU)
- Corresponding author
- Anderson, Peter
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2016
- Pages
- 382-398
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W2506483933
- Cited by
- 1,986
- References
- 45
- Citations by year
- 2026: 127 · 2025: 268 · 2024: 274 · 2023: 292 · 2022: 252 · 2021: 289 · 2020: 194 · 2019: 172 · 2018: 78 · 2017: 34 · 2016: 6
- FWCI
- 33.53
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Lecture notes in computer science (publishedVersion)
- ANU Open Research (Australian National University) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- image captioning, scene graph, human judgment correlation, n-gram overlap, cider, meteors, MS COCO
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
