Events & News
Dissertation Defense
| Category | Lecture |
| Date | Wednesday, April 30, 2014 |
| Time | 9:00 am |
| Concludes | 10:00 am |
| Location | Gould-Simpson 1027 |
| Details | Review Committee: Paul Cohen, Mihai Surdeanu, Kobus Barnard & Ken McAllister |
| Speaker | Anh Tran |
| Title | Doctorial Candidate |
| Affiliation | Computer Science, University of Arizona |
Identifying Latent Attributes from Video Scenes Using Knowledge Acquired from Large Collections of Text Documents
In this work, we explore the task of identifying latent attributes in video scenes, focusing on the mental states of participant actors. We propose a novel approach to the problem based on the use of large text collections as background knowledge and minimal information about the videos, such as activity and actor types, as query context. We formalize the task and a measure of merit that accounts for the semantic relatedness of mental state terms, as well as their distribution weights. We develop and test several largely unsupervised information extraction models that identify the mental states of human participants in video scenes given some contextual information about the scenes. We show that these models produce complementary information and their combination significantly outperforms the individual models, and improves performance over a uniform-probability baseline by almost 75\% on two different datasets. We present an extensive analysis of our models and close with a discussion of our findings.