Published January 1, 2016
| Version v1
Journal article
Open
Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures
Creators
- 1. Univ Trento, Trento, Italy
- 2. Middle E Tech Univ, Istanbul, Turkey
- 3. Univ Amsterdam, NL-1012 WX Amsterdam, Netherlands
- 4. Hacettepe Univ, Ankara, Turkey
- 5. Univ Edinburgh, Edinburgh EH8 9YL, Midlothian, Scotland
- 6. Univ Malta, Msida, Malta
- 7. Univ Copenhagen, DK-1168 Copenhagen, Denmark
Description
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.
Files
bib-499cf9df-1a99-402b-bdfd-4a257f03cf41.txt
Files
(288 Bytes)
| Name | Size | Download all |
|---|---|---|
|
md5:ec5b8a39d33cbef30d236bce693e8711
|
288 Bytes | Preview Download |