Extract robust multi-modality feature is an important task for visual understanding. There has been significant progress in recent years thanks to the rapid progress in machine learning tools and computational resources as well as the availability of large amount of data. Not only is its application performance greatly improved, but also its application fields significantly widened. However, how to learn and combine multi-modality features still facing many challenges in solving real world problems. Lots of real world applications, such as human behavior analysis, robot tracking, object (pedestrian) detection, medical disease diagnosis, often require multiple modalities including RGB cue, depth cue, navigation cue, spatio-temporal structure cue, etc. The goal of this special issue is to bring together researchers working on different modalities to exchange their work and discuss how to leverage and use multi-modality cues to improve visual understanding.
This special issue addressing the problems of visual understanding, such as some visual tasks of human behavior analysis and recognition, robot tracking, object (pedestrian) detection, medical image processing, and their applications with multiple modalities are invited. Both the theoretical and practical progresses are encouraged. The topics of interest for this workshop include but are not limited to the following areas:
Submission portal open: Jun. 20st, 2021
Submission Deadline: Aug. 15st, 2021
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote sensing
Wuhan University, Wuhan, China
E-mail: tuzhigang@whu.edu.cn
State Key Laboratory of Robotics, SIA, Chinese Academy of Sciences (CAS), China
E-mail: congyang@sia.cn
Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore
E-mail: jun_liu@sutd.edu.sg
School of Microelectronics and Communication Engineering, Chongqing University, China
Email: leizhang@cqu.edu.cn
Wormpex AI Research, USA
E-mail: renzhou200622@gmail.com