VIBE - Vision for Interaction and Behaviour undErstanding
Paper submission details:
We invite full papers and position papers. All papers must be submitted through the BMVC provided link (INSERT LINK). The format of the paper is the same as the BMVC main conference (http://bmvc2018.org/submityourpaper.html). All submissions must be in English. The review will be double-blind. The submissions must be in PDF format (make sure that the PDF can be viewed on any platform) and the length should not exceed 9 pages excluding the references. Any appendices must precede the reference list. Papers that do not use the BMVC template, or have more than 9 pages (excluding references) will be rejected without review.
We have witnessed impressive advances in computer vision based recognition and analysis of non-verbal behavioural cues such as gestures, posture, actions, joint attention and facial expressions. However, these cues are rarely analysed holistically and contextually to achieve a deeper understanding of social human behaviour.
The importance of socializing and its impact on decisions, thoughts, and the general wellbeing of individuals are widely recognized. Lack of social interactions is strongly correlated with depression, poor outcomes in stroke survivors, and dementia, for example. There has been increased interest in recent years in developing computer vision-based assistive technologies to monitor the social interactions of people affected by several disorders, and to improve the social interactions of visually impaired people and autistic children by relying on feedback provided by visual data. Development of systems that capture the complexities of human life, anticipate our intentions and adapt to accommodate our needs motivates us to build machines that better interpret our interactions and are capable of interacting with us at a social level.
This opens a new frontier for Social Behaviour Understanding, where major questions are how to capture the diversity and complexity of social life from image data and which image analysis and pattern recognition technologies are effective in this domain. We are organizing a workshop that aims at gathering research progress around those problems that require, in addition to performing an effective visual analysis of basic behavioral cues, to integrate and interpret them jointly.
Topics of interest include, but are not limited to:
- social relation recognition
- face to face and group interactions
- social signal processing
- egocentric vision for social interactions
- multimodal approaches for social interaction and behaviour analysis
- affective computing
- facial and gestural social and emotional cues
- context- dependent human-behaviour models
- social data gathering and ethical concerns
- social robotics
- applications in health and wellbeing, rehabilitation technology, assistive communication
- applications in social media data analysis, lifelogging, human activity monitoring
Paper submission date:7 July 2018
Paper acceptance notification:17 July 2018
Camera Ready Submission:As main conference