In this talk, I will give an overview of recent work that explores how to endow computational systems with the ability to connect natural language and 3D representations. I will talk about a project that develops a unified model for localizing objects in 3D scenes and describing them using natural language. Then, I will quickly summarize other recent work that explores different tasks requiring connections between natural language and 3D representations.
Angel Chang is an Assistant Professor at Simon Fraser University and a Canada CIFAR AI Chair. Her research connects language to visual and 3D representations, and grounds language for embodied agents in indoor environments. She has worked on synthesizing 3D scenes and shapes from natural language, as well as localizing objects in 3D. Her work has been recognized by awards such as the SGP dataset award for ShapeNet and ScanNet.