In 2002 the Pattern Recognition Lab was peacefully preparing to start the work on a new EU Project: Visual Active Memory Processes and Interactive REtrieval — VAMPIRE for short — when the dpa ticker suddenly flashed the sensational line “Universität Erlangen erforscht Vampire.” Within minutes, the institute’s venerable phone system began to glow like a garlic-free Christmas tree. Journalists from boulevard tabloids to public-service broadcasters demanded to know whether the undead were now an EU priority and — if so — how many would be available for on-camera interviews.
Of course, the real VAMPIRE project was neither nocturnal nor sanguine. Funded under EU-IST contract IST-2001–34401 (2002–2005), the consortium — Bielefeld (coord.), Erlangen-Nürnberg, TU Graz and the University of Surrey — set out to endow computer-vision systems with something humans have enjoyed since the their earliest days: memory [1,2]. Instead of “see-snap-forget” pipelines, VAMPIRE proposed a visual active memory capable of storing hierarchical object representations and retrieving them on demand. In other words, a camera that not only notices your lost remote control but actually remembers where it last saw the thing — while you were busy losing it again.
Erlangen’s Pattern Recognition Lab carried two key work-packages. The first was a…