Advancing Dense Prediction Methods for Visual Scene Understanding

Project Description

The task of visual scene understanding is to develop computer algorithms for automatically understanding and analysing the content of scene images and videos, which is a fundamental problem for computer vision and machine learning research. Existing methods for scene understanding are still far from human performance in terms of prediction accuracy, semantic richness and learning efficiency. In this project, we address a number of challenging problems for approaching human-level scene understanding. We will develop novel scene understanding methods based on the recent development of semantic segmentation methods, but go beyond the conventional category-level recognition in existing methods in terms of learning paradigm and semantic concepts for prediction. Specifically, we will focus on instance-level semantic segmentation, high-level semantics recognition including relation recognition and scene description generation, learning from web data with weak annotations, and learning from synthetic data.

Research Technical Area

  • Computer vision

Benefits to the society

Developed techniques can be applied in video surveillance, robotic systems, multimedia applications, and etc. These application will Improve community safety, transportation, manufacturing and generally human living qualities.

Project’s Publications

  1. Chi Zhang, Guosheng Lin, Fayao LiuRui YaoChunhua Shen:
    CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot LearningCVPR 2019: 5217-5226

  2. Zichuan Liu, Guosheng Lin, Sheng YangFayao LiuWeisi LinWang Ling Goh:
    Towards Robust Curve Text Detection With Conditional Spatial Expansion. CVPR 2019: 7269-7278

  3. Chi Zhang, Guosheng Lin, Fayao Liu, Jiushuang Guo, Qingyao Wu, Rui Yao:
    Pyramid Graph Networks with Connection Attentions for Region-Based One-Shot Semantic Segmentation. ICCV 2019

Team’s Principal Investigator

Assistant Professor Lin Guosheng
School of Computer Science and Engineering
College of Engineering Nanyang Technological University

LIN Guosheng is currently an Assistant professor in the School of Computer Science and Engineering, Nanyang Technological University.  He received his Ph.D. degree from The University of Adelaide, Australia in 2014. His research interests are in machine learning and computer vision applications.


Recent Notable Awards

  • Google Ph.D. fellowship, 2014