Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures
Abstract
Automatic description generation from natural images is a challenging problem that has recently received a large amount of interest from the computer vision and natural language processing communities. In this survey, we classify the existing approaches based on how they conceptualize this problem, viz., models that cast description as either generation problem or as a retrieval problem over a visual or multimodal representational space. We provide a detailed review of existing models, highlighting their advantages and disadvantages. Moreover, we give an overview of the benchmark image datasets and the evaluation measures that have been developed to assess the quality of machine-generated image descriptions. Finally we extrapolate future directions in the area of automatic image description generation.
Cite
Text
Bernardi et al. "Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures." Journal of Artificial Intelligence Research, 2016. doi:10.1613/JAIR.4900Markdown
[Bernardi et al. "Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures." Journal of Artificial Intelligence Research, 2016.](https://mlanthology.org/jair/2016/bernardi2016jair-automatic/) doi:10.1613/JAIR.4900BibTeX
@article{bernardi2016jair-automatic,
title = {{Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures}},
author = {Bernardi, Raffaella and Çakici, Ruket and Elliott, Desmond and Erdem, Aykut and Erdem, Erkut and Ikizler-Cinbis, Nazli and Keller, Frank and Muscat, Adrian and Plank, Barbara},
journal = {Journal of Artificial Intelligence Research},
year = {2016},
pages = {409-442},
doi = {10.1613/JAIR.4900},
volume = {55},
url = {https://mlanthology.org/jair/2016/bernardi2016jair-automatic/}
}