SAPIR: Search on Audio-visual content using Peer-to-peer Information Retrieval - EU IST FP6 Project

Web search is dominated today by search giants like Google, Yahoo or MSN that deploy a centralized approach to indexing and utilize text only indexes enriched by page rank algorithms. Consequently, while it is possible to search for audio-visual content, it is limited to associated text and metadata annotations. Supporting real content-based audio-visual search requires media specific understanding and extremely high CPU utilization which would not scale in today’s centralized solutions. SAPIR aims at breaking this technological barrier by developing a large-scale distributed P2P architecture that will make it possible to search in audio-visual content using the query by example paradigm. Our vision is to conduct innovative research that will lead to a technology where end-users are peers that can produce audiovisual content from their mobile devices. This content will be indexed by super-peers across a scalable P2P network to enable content search in real-time while respecting IPR. To this end, SAPIR brings experts in audio-visual content analysis together with world class leaders in Information Retrieval and in P2P technologies. To further improve audio-visual retrieval and navigation SAPIR’s consortium combines experts in Mobile devices technology with experts in Social networking and in IPR to enable a secure and trusted environment.