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
- TCSVTOnline Human Interaction Detection and Recognition with Multiple Cameras IEEE Transactions on Circuits and Systems for Video Technology, 2017.
- ICMEOnline Geometric Human Interaction Segmentation and Recognition In Proceedings of IEEE International Conference on Multimedia and Expo, 2014.
- ISVCPairwise Kernels for Human Interaction Recognition In Advances in Visual Computing, 2013. Oral