Welcome to the iVMCL laboratory at NC State, led by Dr. Tianfu (Matt) Wu who is assistant professor of Electrical and Computer Engineering (ECE) at NC State and affiliated with the Visual Narrative Initiative. Our long-term research focuses on interpretable Visual Modeling, Computing and Learning, often motivated by the tasks of pursuing a unified framework for Artificial Intelligence (A.I.) to ALTER (Ask, Learn, Test, Explain and Refine) recursively in a principled way.

Our current research interests mainly focus on: (i) Interpretable and Universal Representation Learning via Designing and/or Searching Deep Grammar Networks. This line of research is motivated by “the belief that thinking of all kinds requires grammars” and “Grammar in language is merely a recent extension of much older grammars that are built into the brains of all intelligent animals to analyze sensory input, to structure their actions and even formulate their thoughts.” — Professor David Mumford. (ii) Parsimonious and Emergent Representation Learning via Building a Deep Cooperative and Compositional Learning-to-Learn Framework. On top of the research in (i), this line of research is motivated by exploring and exploiting a rich set of tasks organized under principled grammars (i.e., task hierarchy and calculus) to learn-to-learn small details and rich knowledge from little data. Equipped with the two paradigms of representation learning, we envision to develop a unified ALTER framework.

Two papers accepted to CVPR2020

Towards Interpretable Image Synthesis by Learning Sparsely Connected AND-OR Networks, Xianglei Xing, Tianfu Wu, Song-Chun Zhu and Ying Nian WuHolistically-Attracted Wireframe Parsing, …