Unimore logo AImageLab

Personalized Egocentric Video Summarization of Cultural Tour on User Preferences Input




In this paper we propose a new method for customized egocentric video summarization according to specific user preferences, so that different users may extract from the same stream different summaries. Our approach, tailored on cultural heritage scenario, relies on creating a short synopsis of the original video focused on key shots, in which concepts relevant to user preferences can be visually detected and the chronological flow of the original video is preserved. Moreover, we release a new dataset, composed of 48 egocentric streams taken in uncontrolled scenarios, capturing tourists cultural visits in six art cities, with geolocalization information. To best of our knowledge, this is the first egocentric video dataset provided with geolocalization related annotations. Our experimental results show that the proposed approach is able to leverage user's preferences with an accent on storyline chronological flow and on visual smoothness, since the produced summaries have been preferred by 85% of users.

Art Cities Egocentric Dataset(ACED)  

Our original ACED dataset with egocentric video captured in uncontrolled setting during cultural tours in Emilia-Romagna art cities, fully georeferenced and with 26100 annotated frames with informations related to capturer's behavior, presence of cultural items or places of interest and narrativity score. 

Go to ACED dataset