Shot boundary detection The shot boundary detection system in 2007 is basically the same as that of last year. We make three major modifications in the system of this year. First, CUT detector and GT detector use bloc...
详细信息
Shot boundary detection The shot boundary detection system in 2007 is basically the same as that of last year. We make three major modifications in the system of this year. First, CUT detector and GT detector use block based RGB color histogram with the different parameters instead of the same ones. Secondly, we add a motion detection module to the GT detector to remove the false alarms caused by camera motion or large object movements. Finally, we add a post-processing module based on SIFT feature after both CUT and GT detector. The evaluation results show that all these modifications bring performance improvements to the system. High-level feature extraction We try a novel approach, Multi-label Multi-Feature learning (MLMF learning) to learn a joint-concept distribution on the regional level as an intermediate representation. Besides, we improve our Video diver indexing system by designing new features, comparing learning algorithms and exploring novel fusion algorithms. Based on these efforts in improving feature, learning and fusion algorithms, we achieve top results in HFE this year. This year, intelligent multimedia group in Department of computer science and technology, Tsinghua University and scalable statistical computing group in application research lab, MTL, Intel China research Center took part in TRECVID 2007 as a joint team and submitted the results for all of the four tasks. In this paper, the methods of shot boundary detection, high level feature extraction and search are presented while rushes summarization is excluded since it is reported in the workshop during ACM MM 2007.
暂无评论