# Learning Visually Grounded Sentence Representations

Source: [Learning Visually Grounded Sentence Representations](<https://www.sota2.com/research/paper/68fa646e1e209131cea04aef>)

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

Data updated: 2025-10-28T13:56:36.129Z

Authors: Douwe Kiela, Alexis Conneau, Allan Jabri, Maximilian Nickel

Published: 2017-07-19T23:12:57.000Z

## Abstract

We introduce a variety of models, trained on a supervised image captioning corpus to predict the image features for a given caption, to perform sentence representation grounding. We train a grounded sentence encoder that achieves good performance on COCO caption and image retrieval and subsequently show that this encoder can successfully be transferred to various NLP tasks, with improved performance over text-only models. Lastly, we analyze the contribution of grounding, and show that word embeddings learned by this system outperform non-grounded 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/1707.06320>)

[PDF](<https://arxiv.org/pdf/1707.06320.pdf>)