# Image Captioning through Image Transformer

Source: [Image Captioning through Image Transformer](<https://www.sota2.com/research/paper/68fa686f1e209131cea1c33b>)

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

Data updated: 2025-10-25T22:38:00.142Z

Authors: Sen He, Wentong Liao, Hamed R. Tavakoli, Michael Yang, Bodo Rosenhahn, Nicolas Pugeault

Published: 2020-04-29T14:30:57.000Z

## Abstract

Automatic captioning of images is a task that combines the challenges of image analysis and text generation. One important aspect in captioning is the notion of attention: How to decide what to describe and in which order. Inspired by the successes in text analysis and translation, previous work have proposed the \\textit{transformer} architecture for image captioning. However, the structure between the \\textit{semantic units} in images (usually the detected regions from object detection model) and sentences (each single word) is different. Limited work has been done to adapt the transformer's internal architecture to images. In this work, we introduce the \\textbf{\\textit{image transformer}}, which consists of a modified encoding transformer and an implicit decoding transformer, motivated by the relative spatial relationship between image regions. Our design widen the original transformer layer's inner architecture to adapt to the structure of images. With only regions feature as inputs, our model achieves new state-of-the-art performance on both MSCOCO offline and online testing benchmarks.

## 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/2004.14231>)

[PDF](<https://arxiv.org/pdf/2004.14231.pdf>)
