An investigation into event decay from large personal media archives

With the growth of digital lifelogging technologies there are challenges in terms of detecting and annotating real world events from this multimedia lifelog data. In this paper we use the SenseCam, a passively capturing wearable camera, worn around the neck, which captures about 3,000 photos per day, thereby creating a personal lifelog or visual recording of the wearer's life, which could be helpful as a human memory aid. For such a large amount of visual information to be of any value, it needs to be structured into semantic events. In this paper we are particularly interested in how a user's perceptions of real world events decays over time. In particular we investigate several questions including whether data owners have different perceptions of event boundaries to non-owners, whether the passage of time changes what we believe to be events and if so then do we forget about the weakly defined original events. We carry out these investigations using real visual lifelog data gathered and annotated, twice, by three users