ARO Workshop on Semantic Information
Abstract
The goal of this workshop is to bring together researchers in computer vision, machine learning and information theory, to discuss recent progress on defining and computing new notions of information that capture the semantic content of multi-modal data. More specifically, given complex multimodal data (e.g., images, videos, documents, speech, network data) about a scene (e.g., a city, a shopping mall, a political rally) and a class of tasks (e.g., detection, navigation, exploration, search), the goal is to develop an information-theoretic framework for assessing what data modalities and representations are Òmost informativeÓ for these tasks, algorithms for computing such Òinformation representationsÓ from data, and a Bayesian framework for integrating such information representations to produce rich interpretations of complex scenes. Topics of interest include but are not limited to: ¥ Information theoretic approaches to scene understanding ¥ Representation learning ¥ Domain adaptation ¥ Generative adversarial networks as well as the interplay between information and semantic content. ¥ Methods for uncertainty quantification in deep learning and dictionary learning models ¥ Robust multimodal and heterogeneous data fusion
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jul 24, 2019
- Source ID
- W911NF1910354
Entities
People
- Rene Vidal
Organizations
- Army Contracting Command
- Johns Hopkins University
- United States Army