This year's HBU workshop, in addition to covering the main themes of human behavior understanding, specifically deals with computer vision for complex social interactions. Of particular importance is obtaining large amounts of annotated samples required to train such systems, for instance by integration of language and speech with vision. A second topic of interest is the classification of non-verbal signals, gestures and movements. Multimodal approaches that scaffold vision-based systems are of interest, but so are approaches that further our arsenal of computer vision, image and video processing techniques that could be used to understand human behavior.

While different aspects of social interactions are tackled in several venues, this workshop will solicit computer vision solutions that clearly advance the field, and chart the future of computer analysis of complex interactions. Topics of interest include, but are not limited to:

  • Human behavior capture technology and benchmark datasets

  • Social activity detection, tracking, reconstruction, and recognition

  • Social scene representation and understanding

  • Social behavior modeling and prediction

  • Multimodal social signal integration

  • Causality and reciprocity of social interaction

  • Applications of social intelligence