Deep Learning and Multimedia (DLM) Research Group

We are a research lab in the Department of Computer Science at the University of Nebraska Omaha. Our work explores the foundations of deep learning and representation learning, with a focus on content-descriptive and distortion-invariant feature representations. We study how deep models encode and organize information across modalities, and develop methods for self-supervised learning, watermarking, and model attribution. 

We are also interested in advancing "DL + X" research by developing deep learning methods that are explicitly informed by the structures, constraints, and challenges of diverse domains. Rather than simply applying existing deep learning models to new application areas, we are interested in using domain-specific challenges to motivate new representations and learning strategies. By connecting foundational algorithmic development with real-world domain needs, our goal is to create deep learning systems that are more adaptable, interpretable, and effective across disciplines.