Event Detection and Scene Attraction by Very Simple Contextual Cues

We detect and arrange events in private photo archives by putting these photos into context. The problem is seen as a fully auto- mated mining in one’s personal life and behavior. To this end, we build a contextual meaningful hierarchy of events based on personal photos. With the analysis of very simple cues of time, space and perceptual visual appearance we are refining and validating the event borders and their relation in an iterative way. Beginning with discriminating between routine and unusual events, we are able to robustly recognize the basic nature of an event. Further combination of the given cues efficiently gives a hierarchy of events that coincides with the given ground-truth at an F-measure of 0.83 for event detection and 0.70 for its hierarchical representation. We process the given task in a fully unsupervised and computationally inexpensive manner. Using standard clustering and machine learning techniques, sparse events in the collection would tend to be neglected by automated approaches. Opposed to these methods, the proposed approach is invariant to the distribution of the photo collection regarding the sparsity and denseness in time, space and visual appearance. This is improved by introducing a momentum of attraction measure for a meaningful representation of personal events. © ACM