@inproceedings{3a041bfa304f48b8a6598172cb449b4f,
title = "Extracting latent attributes from video scenes using text as background knowledge",
abstract = "We explore the novel task of identifying latent attributes in video scenes, such as the mental states of actors, using only large text collections as background knowledge and minimal information about the videos, such as activity and actor types. We formalize the task and a measure of merit that accounts for the semantic relatedness of mental state terms. We develop and test several largely unsupervised information extraction models that identify the mental states of human participants in video scenes. We show that these models produce complementary information and their combination significantly outperforms the individual models as well as other baseline methods.",
author = "Anh Tran and Mihai Surdeanu and Paul Cohen",
year = "2014",
doi = "10.3115/v1/s14-1016",
language = "English (US)",
series = "Proceedings of the 3rd Joint Conference on Lexical and Computational Semantics, *SEM 2014",
publisher = "Association for Computational Linguistics (ACL)",
pages = "121--131",
booktitle = "Proceedings of the 3rd Joint Conference on Lexical and Computational Semantics, *SEM 2014",
note = "3rd Joint Conference on Lexical and Computational Semantics, *SEM 2014 ; Conference date: 23-08-2014 Through 24-08-2014",
}