Workshop description

Humans form a multitude of social groups through their life and regularly interact with other humans in these groups engaging in social behavior. Social behavior consists of actions that are socially relevant or are situated within an identifiable social context. Interacting or observant humans sense, interpret and understand these behaviors primarily using aural and visual sensory stimuli. While there has been a lot of research on detection, classification and recognition of humans, progressing onto actions, activities and events, most of these works lack grounding in socially relevant contexts. Moreover, this research is largely driven by applications in security & surveillance or in search & retrieval. The time is ripe to ground these technologies in richer social contexts and milieus. This workshop is positioned to show case this rich domain of applications, which will provide the necessary next boost for these technologies. At the same time, it seeks to ground computational models of social behavior in the socio-psychological and neuro-scientific theories of human action and behavior. This will allow us to leverage decades of research in these theoretically and empirically rich fields and to spur interdisciplinary research thereby opening up new problem domains for the vision community. For more details about the program please check the program page.

Call For Papers

Modeling social behavior and interactions is anticipated to be a rewarding and challenging area of research. It would require (a) Modeling of a variety of social contexts and interactions, each involving (b) Two or more intelligent entities (humans) with their context-dependent goals, emotions, affects and behavioral modes; and, (c) Modeling of the interaction between them. These posit many unaddressed challenges for the vision, audio (and multimodal) research community. This workshop will address all aspects of the above research including (but not limited to) the following topics of interest:

    - Computational models of human behavior including those inspired from neuro-scientific and/ or psychosocial theories.
    - Modeling the effect of goals and strategies on computational models of behavior.
    - Machine-Learning for social behavior modeling.
    - Applications of social behavior modeling including in security and surveillance, training and pedagogy, diagnostics and treatment of pathologies.
    - Automatic identification of social contexts, Normative models of behavior, and detection of anomalous behavior.
    - Adoption or fusion of novel or state-of-the-art research in traditional areas of visual cues, speech, vocalics, emotion, affect, detection of multiple humans, poses, actions and activity for modeling and identification of social behaviors.

We call for submission of high-quality papers of standard CVPR length and format in the above and related areas. For more details check important dates & paper submission page.

Contact Us

For any questions regarding the workshop please contact us at csi.cvpr2014@gmail.com or any of the workshop chairs.