Deep Learning and Multimedia (DLM) Research Group
We are a research lab at the Department of Computer Science, University of Nebraska Omaha. Our work explores the foundations of deep learning, representation learning, and multimodal intelligence, focusing on models that connect images with other modalities through content-descriptive and distortion-invariant representations. Ongoing projects include self-supervised representation learning, watermarking, and model attribution for trustworthy.

We also aim for advancing the application of deep learning across diverse domains by designing multimedia-aware architectures that address the unique challenges of different domains such as health, resilience, classroom learning, and biology. By bridging foundational algorithms with applied impact, our goal is to make deep learning systems more adaptable, interpretable, and beneficial across disciplines.