Friday, April 12, 2019 - 10:00am to 11:00am
KEC 1005

Speaker Information

Bo Li
Assistant Professor of Computer Science
University of Southern Mississippi

Abstract

3D models (typically triangular meshes) consist of 3D data to represent 3D objects. They are widely used in a lot of fields such as industrial product design and 3D entertainment. However, it is still challenging to develop effective and efficient 3D shape retrieval algorithms for related applications. This talk introduces an overview of my recent work in 3D shape retrieval, as well as our latest research in 3D scene retrieval, including an ongoing project that applies related deep learning techniques in semantic tree-based large-scale 3D scene retrieval.

Speaker Bio

Dr. Bo Li received his Ph.D. in Computer Science from Nanyang Technological University (Singapore) in 2012. He has more than twelve years’ research experience in Visual Computing, especially 3D Object Retrieval; about nine years’ teaching experience at a university level; and two years’ industrial experience in mobile software testing.

Since 2016, he has been a tenure-track assistant professor of computer science at the University of Southern Mississippi. He was a non-tenure track assistant professor at the University of Central Missouri from 2015 to 2016. From 2012 to 2014, he was a Postdoc in Texas State University. He was a Guest Researcher in NIST from 2011 to 2012.

His research interests mainly fall in the broad area of Artificial Intelligence and Data Science. Recently, he has great interest in applying related Deep Learning techniques in 3D object retrieval and 3D scene understanding. He is the recipient of the top first winners of 2013 and 2016 Eurographics Shape Retrieval Contest (SHREC) competitions in large-scale sketch-based 3D retrieval track, range scan track, and low-cost depth-sensing camera track. He has published more than 40 journal and conference papers, including prestigious ones like CVIU, IJCV, and ICMR.

Now, he is focusing on an ongoing project titled: semantic tree-based large-scale 3D scene retrieval.