AutoCaption: Automatic Caption Generation for Personal Photos
Abstract
AutoCaption is a system that helps a smartphone user generate a caption for their photos. It operates by uploading the photo to a cloud service where a number of parallel modules are applied to recognize a variety of entities and relations. The outputs of the modules are combined to generate a large set of candidate captions, which are returned to the phone. The phone client includes a convenient user interface that allows users to select their favorite caption, reorder, add, or delete words to obtain the grammatical style they prefer. The user can also select from multiple candidates returned by the recognition modules.
Cite
Text
Ramnath et al. "AutoCaption: Automatic Caption Generation for Personal Photos." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014. doi:10.1109/WACV.2014.6835988Markdown
[Ramnath et al. "AutoCaption: Automatic Caption Generation for Personal Photos." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014.](https://mlanthology.org/wacv/2014/ramnath2014wacv-autocaption/) doi:10.1109/WACV.2014.6835988BibTeX
@inproceedings{ramnath2014wacv-autocaption,
title = {{AutoCaption: Automatic Caption Generation for Personal Photos}},
author = {Ramnath, Krishnan and Baker, Simon and Vanderwende, Lucy and El-Saban, Motaz Ahmad and Sinha, Sudipta N. and Kannan, Anitha and Hassan, Noran and Galley, Michel and Yang, Yi and Ramanan, Deva and Bergamo, Alessandro and Torresani, Lorenzo},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2014},
pages = {1050-1057},
doi = {10.1109/WACV.2014.6835988},
url = {https://mlanthology.org/wacv/2014/ramnath2014wacv-autocaption/}
}