11th International Workshop on Human Behavior Understanding (HBU) Call for Papers

********************************************************************
CALL FOR PAPERS - HBU 2021

11th International Workshop on Human Behavior Understanding (HBU)
Focus theme: Multi-source aspects of behavioral understanding

Held in conjunction with WACV 2021
https://lmi.fe.uni-lj.si/hbu2021

Paper submission deadline: November 2nd, 2020
Notifications: November 18th, 2020
*********************************************************************

ORGANIZERS
Abhijit Das, Indian Statistical Institute, Kolkata, India
Qiang Ji, Rensselaer Polytechnic Institute, United States
Umapada Pal, Indian Statistical Institute, Kolkata, India
Albert Ali Salah, Utrecht University, The Netherlands
Vitomir Štruc, University of Ljubljana, Slovenia

ABOUT
Domains for human behaviour understanding predominantly (e.g.,
multimedia, human-computer interaction, robotics, affective computing
and social signal processing) rely on advanced pattern recognition
techniques to automatically interpret complex behavioural patterns
generated when humans interact with machines or with other
agents. This is a challenging research area where many issues are
still open, including the joint modelling of behavioural cues taking
place at different time scales, the inherent uncertainty of machine
detectable evidence of human behaviour, the mutual influence of people
involved in interactions, the presence of long term dependencies in
observations extracted from human behaviour, and the important role of
dynamics in human behaviour understanding. Computer vision is a key
technology for analysis and synthesis of human behaviour but stands to
gain much from multi-modality and multi-source processing, in terms of
improving accuracy, resource use, robustness, and contextualization.

This workshop, organized as part of WACV 2021, will gather researchers
dealing with the problem of modelling human behaviour under its
multiple facets (expression of emotions, display of relational
attitudes, the performance of an individual or joint actions, etc.),
with particular attention to multi-source aspects, including
multi-sensor, multi-participant and multi-modal settings. Example
challenges are the additional resource and robustness constraints,
explorations in information fusion, social and contextual aspects of
interactions, and building multi-source representations of social and
affective signals with the goal of advancing the state-of-the-art.

The HBU workshops, previously organized as satellite events to major
conferences in different disciplines such as ICPR'10, AMI'11,
IROS'12, ACMMM'13, ECCV'14, UBICOMP'15, ACMMM'16,
FG'18, ECCV'18, ICCV'19 have a unique aspect of fostering
cross-pollination of disciplines, bringing together researchers from a
variety of fields, such as computer vision, HCI, artificial
intelligence, pattern recognition, interaction design, ambient
intelligence, psychology and robotics. The diversity of human
behaviour, the richness of multimodal data that arises from its
analysis, and the multitude of applications that demand rapid progress
in this area ensure that the HBU Workshops provide a timely and
relevant discussion and dissemination platform. For HBU@WACV, we
particularly solicit contributions on human behaviour understanding
that combine multiple sources of information, be it across modalities,
sensors, or subjects under observation. The workshop solicits papers
on general topics related to human behaviour understanding, but with a
distinct focus on multi-source solutions.

TOPICS OF INTEREST
Topics of interest include, but are not limited to:

    + Multimodal solutions for human behaviour modelling and analysis
    + Multimodal solutions towards behavioural biometrics (gait, handwriting, keystroke dynamics, etc.)
    + Methods for multi-instance learning in behavioural understanding,
    + Analysis of multi-participant settings and of social interactions,
    + Multi-instance representation for characterizing human health, empathy,
    + Deep learning for multi-party interactions
    + Multimodal deep learning for behaviour understanding
    + Adversarial learning approaches
    + Related sensor technologies
    + Information fusions approach for behaviour analysis
    + Realistic behaviour synthesis in multiple modalities and for multi-party settings
    + Mobile and wearable systems for behaviour monitoring
    + Datasets and benchmarks
    + Related applications

PAPER SUBMISSION
Submission instruction can be found at 
https://lmi.fe.uni-lj.si/hbu2021/paper-submission/

Please feel free to contact for any further details.

Abhijit Das, Qiang Ji, Umapada Pal, Albert Ali Salah, Vitomir Štruc
HBU 2021 Organizers