A watershed-based social events detection method with support of external data sources

In this paper, a watershed-based method with support from external data sources is proposed to detect Social Events defined by MediaEval 2012. This method is based on two main observations: (1) people cannot be involved in more than one event at the same time, and (2) people tend to introduce similar annotations for all images associated to the same event. Based on these observations, the whole metadata is turned to an image so that each row contains all records belonging to one user; and these records are sorted by time. Therefore, the social event detection is turned to watershed based image segmentation, where Markers are generated by using (keywords, location) features with support of external data sources, and the Flood progress is carried on by taking into account (tags set, time) features. The high precision (> 86%), and the acceptable recall (≈ 50%) show the high effectiveness of the proposed method.