YouTube has meant that we are now becoming accustomed to searching for video clips, and finding them, for both work and leisure pursuits. But YouTube, like the Internet Archive, OpenVideo and almost everything other video library, doesn't use video to find video, it uses metadata, usually based on user generated content (UGC). But what if we don't know what we're looking for and the metadata doesn't help, or we have poor metadata or no UGC, can we use the video to find video ? Can we automatically derive semantic concepts directly from video which we can use for retrieval or summarisation ? Many dozens of research groups throughout the world work on the problems associated with content-based video search, content-based detection of semantic concepts, shot boundary detection, content-based summarisation and content-based event detection. In this presentation we give a summary of the achievements of almost a decade of research by the TRECVid community, including a report on performance of groups in different TRECVid tasks. We present the modus operandi of the annual TRECVid benchmarking, the problems associated with running an annual evaluation for nearly 100 research groups every year and an overview of the most successful approaches to each task.