Title: 3D Scene Image Cognition and Multi-modal Learning

Abstract:  Spatial structure and semantics of object in complex environment remains a challenging task. Prof. Huimin Ma’s lab is currently interested in knowledge based object detection, which includes salient object detection, semantic parts model, multi-modal and multi-view learning, and so on. Her researches have been used in autonomous driving in heavy occlusion city scenes.

Biography: Huimin Ma is an associate professor of Department of Electronic Engineering of Tsinghua University, and the director of 3D Image Lab. She received the Ph.D. degrees from Beijing Institute of Technology in 2001. She worked as a visiting scholar in University of Pittsburgh in 2011. She is also the secretary-general of China Society of Image and Graphics.

Her research and teaching interests include 3-D object recognition and tracking, system modeling and simulation, psychological base of image cognition. She achieved the highest award of AI of China (Wu Wenjun artificial intelligence science and technology innovation award, First Class), in 2016. Her team achieved top performance in the international evaluation of object detection for autonomous driving on KITTI Benchmark in 2015.