Kernel-Based Linear Neighborhood Propagation for Semantic Video Annotation

The insufficiency of labeled training samples for representing the distribution of the entire data set (include labeled and unlabeled) is a major obstacle in automatic semantic annotation of large-scale video database. Semi-supervised learning algorithms, which attempt to learn from both labeled and unlabeled data, are promising to solve this problem. In this paper, we present a novel semi-supervised approach named Kernel based Local Neighborhood Propagation (Kernel LNP) for video annotation. This approach combines the consistency assumption and the Local Linear Embedding (LLE) method in a nonlinear kernel-mapped space, which improves a recently proposed method Local Neighborhood Propagation (LNP) by tackling the limitation of its local linear assumption on the distribution of semantics. Experiments conducted on the TRECVID data set demonstrate that this approach can obtain a more accurate result than LNP for video semantic annotation.