# SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding

Source: [SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding](<https://www.sota2.com/research/paper/68fa65d61e209131cea0c9f6>)

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

Data updated: 2025-10-25T21:36:37.771Z

Authors: Baohua Sun, Lin Yang, Michael Lin, Charles Young, Patrick Dong, Wenhan Zhang, Jason Dong

Published: 2019-05-25T03:57:16.000Z

## Abstract

Language and vision are processed as two different modal in current work for image captioning. However, recent work on Super Characters method shows the effectiveness of two-dimensional word embedding, which converts text classification problem into image classification problem. In this paper, we propose the SuperCaptioning method, which borrows the idea of two-dimensional word embedding from Super Characters method, and processes the information of language and vision together in one single CNN model. The experimental results on Flickr30k data shows the proposed method gives high quality image captions. An interactive demo is ready to show at the workshop.

## 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/1905.10515>)

[PDF](<https://arxiv.org/pdf/1905.10515.pdf>)