Transforming Personal Artifacts into Probabilistic Narratives
Abstract
An approach focused on inferring probabilistic narratives from personal artifacts (including photographs) is presented in this work using personal photos metadata (timestamp, location, and camera parameters), formal event models, mobile device connectivity, external data sources and web services. We introduce plausibility measure — the occurrence-likelihood of an event node in the output graph. This measure is used to find the best event among the merely possible candidates. In addition, we propose a new clustering method that uses timestamp, location, and camera parameters in the EXIF header of the input photos to create event boundaries used to detect events. 1
Cite
Text
Rafatirad and Laskey. "Transforming Personal Artifacts into Probabilistic Narratives." Conference on Uncertainty in Artificial Intelligence, 2013.Markdown
[Rafatirad and Laskey. "Transforming Personal Artifacts into Probabilistic Narratives." Conference on Uncertainty in Artificial Intelligence, 2013.](https://mlanthology.org/uai/2013/rafatirad2013uai-transforming/)BibTeX
@inproceedings{rafatirad2013uai-transforming,
title = {{Transforming Personal Artifacts into Probabilistic Narratives}},
author = {Rafatirad, Setareh and Laskey, Kathryn B.},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2013},
pages = {29-38},
url = {https://mlanthology.org/uai/2013/rafatirad2013uai-transforming/}
}