# Intrinsic Image Captioning Evaluation

Source: [Intrinsic Image Captioning Evaluation](<https://www.sota2.com/research/paper/68fa68f41e209131cea1f4bd>)

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

Data updated: 2025-10-25T22:49:52.437Z

Authors: Chao Zeng, Sam Kwong

Published: 2020-12-14T08:36:05.000Z

## Abstract

The image captioning task is about to generate suitable descriptions from images. For this task there can be several challenges such as accuracy, fluency and diversity. However there are few metrics that can cover all these properties while evaluating results of captioning models.In this paper we first conduct a comprehensive investigation on contemporary metrics. Motivated by the auto-encoder mechanism and the research advances of word embeddings we propose a learning based metrics for image captioning, which we call Intrinsic Image Captioning Evaluation(I2CE). We select several state-of-the-art image captioning models and test their performances on MS COCO dataset with respects to both contemporary metrics and the proposed I2CE. Experiment results show that our proposed method can keep robust performance and give more flexible scores to candidate captions when encountered with semantic similar expression or less aligned semantics. On this concern the proposed metric could serve as a novel indicator on the intrinsic information between captions, which may be complementary to the existing ones.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2012.07333>)

[PDF](<https://arxiv.org/pdf/2012.07333.pdf>)