题 目: Learning based 3D scene understanding and beyond
主 讲: Jianfei Cai Associate Professor
时 间：2017年6月16日（周五）上午 10：00
报告摘要: 3D scene understanding is an important and challenging task in computer vision with many applications such as autonomous driving, robotics, surveillance and telepresence. With the help of deep learning technology, the performance of 3D scene understanding has been greatly advanced. In this talk, I will introduce some of our recent works along this line such as multi-model feature fusion frameworks for RGB-D object recognition, RGB-D scene classification and RGB-D action recognition as well as our very recent work on learning based 3D face reconstruction.
主讲人简介: Jianfei received his PhD degree from the University of Missouri-Columbia. He is a faculty with School of Computer Engineering, Nanyang Technological University, Singapore. He has served as the Head of Visual & Interactive Computing Division and the Head of Computer Communication Division at NTU. His major research interests include computer vision, multimedia and machine learning. He has published more than 200 technical papers in international conferences and journals. He is a co-recipient of paper awards in ACCV, IEEE ICIP and MMSP. He has served as the leading Technical Program Chair for IEEE International Conference on Multimedia & Expo (ICME) 2012 and the leading General Chair for Pacific-rim Conference on Multimedia (PCM) 2012. He has been an Associate Editor for IEEE Trans on Image Processing (T-IP) since 2013 and has served as an Associate Editor for IEEE Trans on Circuits and Systems for Video Technology (T-CSVT) during 2006-2013.