happy sad


  • 08/22/2020 - Please complete a brief survey to help us understand the needs of the research community in terms of data. We plan to provide more datasets in the future. Thanks.
  • 08/17/2020 - Workshop program is posted below.
  • 02/20/2020 - Workshop is announced, with invited speakers confirmed.
  • Introduction

    Understanding human bodily expressed emotion is of great importance in the field of computer vision, robotics, psychology/psychiatry, and graphics. This BEEU workshop focuses on computer vision and machine learning methods for understanding human bodily expressed emotion.

    We invite submissions of 1) original research papers of unpublished work and 2) extended abstracts of preliminary work. The papers will be peer-reviewed and, if accepted, published in the ECCV workshop proceedings. Accepted submissions will be presented as orals/posters/spotlights at the workshop. The covered topics include but are not limited to:

  • Bodily expression open datasets
  • Computer vision methods to understand bodily expression
  • Expressive human pose representation
  • Human movements coding system
  • Applications in robotics, autonomous driving, and medicine, etc.
  • Algorithmic fairness and data ethics related to emotion modeling
  • Data sharing and open science with human subject data

  • We invite submissions of results to a challenge based on the BoLD (Body Language Dataset). Please visit the challenge website to learn more about the dataset. We have defined an evaluation protocol. The results will be announced during the workshop and the authors of the winning methods will be invited to present their approaches. A paper with an analysis of the results will be published in the workshop proceedings for a selected few winning teams.

    We expect that 70% of the accepted papers will be from the regular paper and abstract tracks and 30% from the challenge track.


    Please click HERE for the workshop program. We strongly encourage you to view the available talk videos from the ECCV site before the Zoom sessions. Prof. Malik's talk will be live on Zoom.

    Invited Speakers


    Jitendra Malik (keynote)

    Arthur J. Chick Professor of Electrical Engineering & Computer Sciences (EECS),
    University of California at Berkeley.


    Norman Badler (keynote)

    Rachleff Professor of The Department of Computer and Information Science (CIS),
    University of Pennsylvania.


    Nadia Berthouze

    Professor & Deputy Director of UCLIC,
    University College London.


    Kerri L. Johnson

    Professor & Department Chair of Communication and Psychology, University of California, Los Angeles.


    Agata Lapedriza

    MIT Media Lab & Associate Professor from Universitat Oberta de Catalunya.


    Xin Lu

    Engineering Manager and Scientist,
    Adobe Research.


    Nikolaus Troje

    Professor of Department of Biology,
    York University.

    Demonstration of Movement Analysis


    Making Meaning with Machines in Motion: Workshops in Movement Analysis

    Amy LaViers and Cat Maguire, University of Illinois at Urbana-Champaign

    Interest in Laban Movement Analysis and Bartenieff Fundamentals in technology has been steadily growing over the past decades. Researchers, developers, designers, and artists interested in understanding principles of choreography and their applications to the design of new embodied systems and interfaces look to this body of knowledge for information in how people create meaning through movement; rather than measurements of the velocity of body parts or of the internal firings of neurons, this body of work focuses on the aspects of movement consciously noticed by human movers. In work, we expose researchers to different aspects of choreography, improvisation and the Laban/Bartenieff Movement System as a tool for meaning-making through recognizing patterns, reconciling paradox, contexting, and gaining respect for the complexity of human movement. We approach these ideas through both functional and expressive movement experiences that can illuminate the body as the basis for our “knowing” of the world in order to inform engineering work. Thus, we provide structured experiences in movement alongside the introduction of a taxonomy for more objectively describing features of movement observed in these experiences. Through a short demonstration at this workshop, we will highlight how embodied movement is essential to analyzing movement and offer information about upcoming online-learning opportunities in movement analysis.

    Important Dates

    Paper submission deadline (research paper and abstract tracks): 4 July 2020 (16:59 US Pacific Time or 23:59 UTC-0)
    Paper submission deadline (challenge track): 4 August 2020 (16:59 US Pacific Time or 23:59 UTC-0)
    Paper acceptance notification: 20 August 2020
    Camera-ready submission deadline: 12 September 2020 (16:59 US Pacific Time or 23:59 UTC-0)
    Workshop date: 23 August 2020 (morning)


    Papers accepted by the workshop will be published in the ECCV 2020 workshop proceedings, along with other ECCV 2020 workshops. Submissions must use the ECCV 2020 LaTeX or Word templates. All submissions will be handled electronically via the MSR CMT system. (https://cmt3.research.microsoft.com/BEEU2020) Authors will be required to transfer copyrights for any papers published in the conference proceedings.

    For any submission that is based on a declined submission to the main ECCV 2020 conference, authors are required to submit a copy of the reviews from the main conference along with a statement documenting any changes made in the workshop submission from the original ECCV submission to address the review comments.

    Call for Papers

  • As with the ECCV main conference, papers must be no more than 14 pages (excluding references).
  • Submissions will be subjected to a double blind peer review process. Authors should guarantee that a substantially similar work has not been previously published nor is under review.

  • Call for Extended Abstracts

  • In addition to regular papers, we also invite extended abstracts of ongoing, unfinished preliminary work. This can be an opportunity for researchers to promote their new ideas to an interested audience.
  • Extended abstracts are limited to 4 pages, including references.

  • Call for Challenge Participation

  • We invite authors to submit empirical results to our challenge based on the BoLD dataset.
  • Authors are strongly encouraged to concurrently submit a paper describing the methods to the workshop.
  • If a paper is submitted, it must be no more than 14 pages (excluding references).
  • Top-performing results will be accepted to present at the workshop.

  • Organizers

    James Z. Wang, College of Information Sciences and Technology, Penn State University, jwang (at) ist.psu.edu
    Reginald B. Adams, Jr., Department of Psychology, Penn State University, rba10 (at) psu.edu
    Yelin Kim, Amazon Lab 126, kimyelin (at) amazon.com

    Others contributed to the workshop organization are: Jia Li, Yu Luo, Michelle G. Newman, and Sarah M. Rajtmajer of Penn State University.

    Contact Us

    James Z. Wang
    College of Information Sciences and Technology
    E354 Westgate Building, Penn State, University Park, PA 16802
    Email: jwang (at) ist.psu.edu Please use subject line "BEEU2020".

    Copyright © 2020 James Z. Wang Research Group, The Pennsylvania State University, University Park, PA, USA.

    We thank Xinye Zheng, Yu Luo, Mohammad Kamani, and Jianbo Ye for assistance. Built on Business Frontpage by Start Bootstrap