Photo stream alignment for collaborative photo collection and sharing in social media

With the popularity of digital cameras and camera phones, it i common for different people, who may or may not know eac other, to attend the same event and take pictures and videos fro different spatial or personal perspectives. Within the realm of so cial media, it is desirable to enable these people to share their pic tures and videos in order to enrich memories and facilitate soci networking. However, it is cumbersome to manually manage thes photos from different cameras, of which the clocks settings are o ten not calibrated. In this paper, we propose an automatic algorith to accurately align different photo streams or sequences from di ferent photographers for the same event in chronological order on common timeline, while respecting the time constraints within eac photo stream. Given the preferred similarity measure (e.g. visua temporal, and spatial similarities), our algorithm performs phot stream alignment via matching on a sparse representation grap that forces the data connections to be sparse in a explicit fashion We evaluate our algorithm on real-world personal online album for thirty-six events and demonstrate its efficacy in automaticall facilitating collaborative photo collection and sharing.