Late fusion of heterogeneous methods for multimedia image retrieval
MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
| Hi-index | 0.00 |
It is our great pleasure to welcome you to the first TRECVID Video Summarization workshop, held in conjunction with ACM Multimedia 2007. Although this is the first TRECVID summarization workshop, it is only the next in an annual series of TRECVID evaluation workshops going back to 2001. TRECVID is an annual event whereby the effectiveness of tasks relative to content-based video management is benchmarked in an open, metrics-based forum. TRECVID attracts over 60 research groups from across the world each year in an activity in which those groups can assess the relative effectiveness of their techniques against the best in the world. TRECVID has been instrumental in helping to push back the boundaries in tasks like shot boundary detection, video search and automatic concept/feature detection and has been a catalyst in helping the research community to achieve improvements in each of these in recent years. This year is the first year that TRECVID has addressed the task of automatic video summarization and in this workshop we shall see the results of 22 research groups from 14 countries as they address the challenge of automatically summarizing raw, unprocessed rushes video down to at most 4% of the original content duration. This is also the first year that TRECVID has held one of its workshops outside the closed confines of the NIST campus in Gaithersburg, USA. We are delighted that doing this gives us the opportunity to showcase our collective activities to a wider audience, not just our own participants, and we believe that collocating with the ACM Multimedia conference is an ideal forum for this. We thank the ACM Multimedia workshop chairs for affording us this opportunity. The TRECVID summarization workshop is not like any other workshop in that many or most of the workshop participants will have worked to complete a shared task, namely the automatic summarization of a collection of input videos. This means that we expect to have a highly interactive, highly involved workshop with much offline discussion and idea brainstorming. We are looking forward to it.