Domains for human behavior 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 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. Computer vision is a key technology for analysis and synthesis of human behavior 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 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 multi-source aspects, including multi-sensor, multi-participant and multi-modal settings. Example challenges are 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 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. For HBU@WACV, we particularly solicit contributions on human behavior understanding that combine multiple sources of information, be it across modalities, sensors, or subjects under observation.
For enquiries please send an e-mail to hbu2021 [at] googlegroups [dot] com