Extracting Latent Attributes from Video Scenes Using Text as Background Knowledge
Anh Tran, Mihai Surdeanu, Paul Cohen · 2014
We explore the novel task of identify-ing 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 re-latedness of mental state terms. We de-velop and test several largely unsupervised information extraction models that iden-tify the mental states of human partici-pants in video scenes. We show that these models produce complementary informa-tion and their combination significantly outperforms the individual models as well as other baseline methods. 1