# Quality Estimation for Image Captions Based on Large-scale Human Evaluations

Source: [Quality Estimation for Image Captions Based on Large-scale Human Evaluations](<https://www.sota2.com/research/paper/68fa6a0f1e209131cea25e73>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:15:37.395Z

Authors: Tomer Levinboim, Ashish V. Thapliyal, Piyush Sharma, Radu Soricut

Published: 2019-09-08T06:55:53.000Z

## Abstract

Automatic image captioning has improved significantly over the last few years, but the problem is far from being solved, with state of the art models still often producing low quality captions when used in the wild. In this paper, we focus on the task of Quality Estimation (QE) for image captions, which attempts to model the caption quality from a human perspective and without access to ground-truth references, so that it can be applied at prediction time to detect low-quality captions produced on previously unseen images. For this task, we develop a human evaluation process that collects coarse-grained caption annotations from crowdsourced users, which is then used to collect a large scale dataset spanning more than 600k caption quality ratings. We then carefully validate the quality of the collected ratings and establish baseline models for this new QE task. Finally, we further collect fine-grained caption quality annotations from trained raters, and use them to demonstrate that QE models trained over the coarse ratings can effectively detect and filter out low-quality image captions, thereby improving the user experience from captioning systems.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Caption-level correlation with human judgment on Flickr 8K tie-free (test)](<https://www.sota2.com/research/sota/caption-level-correlation-with-human-judgment-on-flickr-8k-tie-free-test.md>): Caption-level correlation with human judgment; Flickr 8K tie-free (test); Kendall's Tau: 0.655.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1909.03396>)

[PDF](<https://arxiv.org/pdf/1909.03396.pdf>)