Millions of people find the digital media that they want and need via social networks, and rely on recommendations to sort a flood of posts, friends, multimedia and promoted content. Today's users, however, need a new generation of smart recommendations that are able to keep pace with their moment-to-moment needs in their fast-moving, dynamically developing, mobile worlds. Achieving such social smartfeeds requires facing the grand challenge of providing recommendations that are simultaneously real-time, large-scale, socially informed, interactive and context aware.CrowdRec addresses this challenge by pioneering a breed of algorithms that combine crowdsourcing and recommendation algorithms to achieve a new generation of social smartfeeds for access and exchange of digital media in social networks. The key insight of CrowdRec is that, in order to achieve the dense, high-quality, timely information required for a truly useful social smartfeed, it is necessary to go beyond passive information collection and also beyond users' immediate social circles. Instead, the necessary information can be actively acquired by using crowdsourcing to solicit input and feedback from the wider community. CrowdRec algorithms create a symbiosis between users and content: they establish reciprocal relationships that both satisfy users' digital media needs and connect media with users able and willing to contribute the information necessary to improve access and exchange for the overall community.The project pursues three scientific and technical objectives: "Stream Recommendation": exploiting the ability of recommender system's to process usage patterns to create social smartfeeds useful in large-scale social networks; "Crowd Engagement": designing algorithms that engage users to generate information needed for smartfeeds; "Deployment and Validation": creating a both a reference implementation to support research and a real-world social networks for large-scale user trials.CrowdRec achieves its ambitious goals by bringing academic, industry and SME partners with longstanding expertise in social and context-aware recommendation together with two large social networks with the high volume of media data flowing in live user communities (one > 14 million members and one > 20 thousand members) necessary for "in vivo" development and evaluation of CrowdRec technology.