Description
Domains for human behavior understanding (e.g. multimedia, human-computer interaction, robotics, affective computing and social signal processing) predominantly rely on advanced pattern recognition techniques to automatically interpret complex behavioral 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 modeling of behavioral cues taking place at different time scales, the inherent uncertainty of machine detectable evidences of human behavior, the mutual influence of people involved in interactions, the presence of long term dependencies in observations extracted from human behavior, and the important role of dynamics in human behavior understanding. For clinical and behavioral sciences, not only accurate behavior analysis is essential, but further aspects like explainability, privacy-aware processing, and fairness are often required. The development of explainable and interpretable models for social behavior analysis would result in more trustable solutions that could be adopted by domain experts for informed decision making. Furthermore, public datasets are often difficult to obtain and share in a privacy-aware manner (particularly during Covid-19), which hampers scientific progress.
This workshop, organised as part of ICPR 2022, and endorsed by IAPR, will gather researchers dealing with the problem of modeling human behavior under its multiple facets (expression of emotions, display of relational attitudes, performance of individual or joint actions, etc.), with particular attention to clinical settings and tools usable for behavioral scientists. Examples of challenges are automatic labeling, annotation, and reporting systems, datasets acquired from real or simulated clinical conditions, systems that focus on the analysis of interaction dynamics, early diagnosis and intervention systems, augmented telepresence, personalized agents, and multimodal approaches.
The HBU workshops, previously organized as satellite events to major conferences in different disciplines (ICPR'10, AMI'11, IROS'12, ACMMM'13, ECCV'14, UBICOMP'15, ACMMM'16, FG'18, ECCV'18, ICCV'19, WACV'21) have a unique aspect of fostering cross-pollination of disciplines, bringing together researchers from a variety of fields, such as computer vision, pattern recognition, HCI, artificial intelligence, interaction design, ambient intelligence, social signal processing, psychology, and robotics. The diversity of human behavior, 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.
Contact
Dr. Albert Ali Salah
Information and Computing Sciences
Utrecht University, The Netherlands
Computer Engineering
Bogazici University, Turkey
E-mail: a.a.salah [at] uu.nl
