# Technical Report: Image Captioning with Semantically Similar Images

Source: [Technical Report: Image Captioning with Semantically Similar Images](<https://www.sota2.com/research/paper/68fa61f91e209131ce9f6b81>)

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

Data updated: 2025-10-25T20:09:28.486Z

Authors: Martin Kol\\'a\\v{r}, Michal Hradi\\v{s}, Pavel Zem\\v{c}\\'ik

Published: 2015-06-12T11:51:16.000Z

## Abstract

This report presents our submission to the MS COCO Captioning Challenge 2015. The method uses Convolutional Neural Network activations as an embedding to find semantically similar images. From these images, the most typical caption is selected based on unigram frequencies. Although the method received low scores with automated evaluation metrics and in human assessed average correctness, it is competitive in the ratio of captions which pass the Turing test and which are assessed as better or equal to human captions.

## 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/1506.03995>)

[PDF](<https://arxiv.org/pdf/1506.03995.pdf>)