Hang Li

I am a PhD student advised by Prof. Volker Tresp at Ludwig Maximillian University of Munich (LMU) and Siemens AG. I work on cognitive deep learning, knowledge graphs, and computer vision.

I acquired my master's degree in Robotics, Cognition, Intelligence at the department of computer science at Technical University of Munich. My master's thesis is about scene graph reasoning for visual question answering, supervised by Prof. Stephan Günnemann and Prof. Volker Tresp.

Email  /  CV  /  Google Scholar  /  Github  /  Twitter  /  LinkedIn

My research focuses on a wide range of deep learning topics, particularly in cognitive deep learning, multimodal knowledge graphs, representation learning, and visual question answering. I'm interested in the intersection of cognitive neuroscience and artificial intelligence.

We present a unified computational theory of an agent’s perception and memory. Episodic memory and semantic memory evolved as emergent properties in a development to gain a deeper understanding of sensory information, to provide a context, and to provide a sense of the current state of the world.

We find that Graphhopper outperforms state-of-the-art scene graph reasoning model on both manually curated and automatically generated scene graphs by a significant margin.

We propose a novel method that approaches the VQA task by performing context-driven, sequential reasoning based on the objects and their semantic and spatial relationships present in the scene.

Last updated: 03 Nov 2021
Website template from Jon Barron