Phrase-based Image Captioning
Remi Lebret, Pedro Pinheiro, Ronan Collobert
Abstract
Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing. In this paper, we present a simple model that is able to generate descriptive sentences given a sample image. This model has a strong focus on the syntax of the descriptions. We train a purely linear model to embed an image representation (generated from a previously trained Convolutional Neural Network) into a multimodal space that is common to the images and the phrases that are used to described them. The system is then able to infer phrases from a given image sample. Based on the sentence description statistics, we propose a simple language model that can produce relevant descriptions for a given test image using the phrases inferred. Our approach, which is considerably simpler than state-of-the-art models, achieves comparable results in two popular datasets for the task: Flickr30k and the recently proposed Microsoft COCO.
BibTeX
@InProceedings{pmlr-v37-lebret15,
title = {Phrase-based Image Captioning},
author = {Lebret, Remi and Pinheiro, Pedro and Collobert, Ronan},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning},
pages = {2085--2094},
year = {2015},
editor = {Bach, Francis and Blei, David},
volume = {37},
series = {Proceedings of Machine Learning Research},
address = {Lille, France},
month = {07--09 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v37/lebret15.pdf},
url = {https://proceedings.mlr.press/v37/lebret15.html},
abstract = {Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing. In this paper, we present a simple model that is able to generate descriptive sentences given a sample image. This model has a strong focus on the syntax of the descriptions. We train a purely linear model to embed an image representation (generated from a previously trained Convolutional Neural Network) into a multimodal space that is common to the images and the phrases that are used to described them. The system is then able to infer phrases from a given image sample. Based on the sentence description statistics, we propose a simple language model that can produce relevant descriptions for a given test image using the phrases inferred. Our approach, which is considerably simpler than state-of-the-art models, achieves comparable results in two popular datasets for the task: Flickr30k and the recently proposed Microsoft COCO.}
}