A novel framework for semantic-based video retrieval
Xiaoming Nan, Zhicheng Zhao, Anni Cai, Xiaohui Xie · 2009
In this paper, a novel framework for semantic-based video retrieval is proposed. 15 low-level visual features on different levels are extracted and a supervised SVM classifier is trained for each feature. We have explored early fusion schemes between SIFT and SURF, and evaluated 4 kinds of later fusion strategies. Experiments on TRECVID dataset show that the proposed system is effective and stable.