Multi-visual-Modality Human Activity Understanding (MMHAU)

ACCV 2020 Workshop, Kyoto, Japan


Human activity analysis (HAA) in videos is a long-time hot research topic. There has been tremendous 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, human activity understanding still faces many challenges in solving real world problems. Many real world applications, such as attention understanding and suspicious activity recognition in a retail store, often require multiple visual modalities including facial expression, head pose, hand pose, body pose, and human action. The goal of this workshop is to bring together researchers working on different visual modalities to exchange their work and discuss how to leverage multiple visual modalities to improve human activity understanding. The workshop will be a great forum for researchers to find synergies among each other’s work and explore potential collaborations.

Papers addressing the issues of human gesture, pose, action, event, and their applications with multiple visual 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 above list items.

Call for Papers



The Best five papers will be recommended to a special issue on Journal of Visual Communication and Image Representation (JVCIR, IF=2.479)

Scope and Topics



CMT Submission Website: Link

Official Website: Link

Submission Guidelines: Link

Important Dates

Paper Submission Deadline

September 25, 2020

Notification to Authors

October 9, 2020

Camera-Ready Deadline

October 16, 2020

Workshop Date

Dec. 3-4, 2020

Accepted Papers

To Be Decided.

Organizers and Speakers


Zhigang Tu, Ph.D.

State Key Laboratory of

Information Engineering in

Surveying, Mapping and

Remote sensing,

Wuhan University, Wuhan, China


Junsong Yuan, Ph.D 

Computer Science and Engineering Department

University at Buffalo, State University of New York, USA


Zicheng Liu, Ph.D

Principal Research Manager

Microsoft AI&R Ambience Intelligence, USA


Invited Speakers

Jiaying Liu

Peking University, China. Email:, Final

Jun Liu,

Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore.

Email:, Tentative


Duration: full day

Committee Members:


This workshop is proudly sponsored by Infinova.