Detection and recognition of continuous activities from video is a core problem to address for enabling intelligent systems that can extract and manage content fully automatically. Recent years have seen a concentration of works revolving around the problem of recognizing single-person actions, as well as group activities. On the other hand, the area of modeling the interactions between two people is still relatively unexplored. While there are a lot of large datasets on single person action recognition, the computer vision community is deprived from a large and challenging binary human interactions dataset. Therefore, we introduce a new video dataset recording several binary human interactions from four different views.

Some components of the dataset are in this repository

Related publications include (Motiian et al., 2013) , (Siyahjani et al., 2014) , (Motiian et al., 2017).


  1. TCSVT
    Online Human Interaction Detection and Recognition with Multiple Cameras Motiian, S., Siyahjani, F., Almohsen, R., and Doretto, G. IEEE Transactions on Circuits and Systems for Video Technology, 2017. abstract bibTeX pdf
  2. ICME
    Online Geometric Human Interaction Segmentation and Recognition Siyahjani, F., Motiian, S., Bharthavarapu, H., Sharlemin, S., and Doretto, G. In Proceedings of IEEE International Conference on Multimedia and Expo, 2014. abstract bibTeX pdf
  3. ISVC
    Pairwise Kernels for Human Interaction Recognition Motiian, S., Feng, K., Bharthavarapu, H., Sharlemin, S., and Doretto, G. In Advances in Visual Computing, 2013. Oral abstract bibTeX pdf html doi