FXPAL Experiments for TRECVID 2004

For shot boundary detection, our approach combines pairwise similarity analysis and supervised classification. Using primitive low-level image features, we build secondary features based on inter-frame dissimilarity. The secondary features are motivated by prior work on media segmentation in which a kernel function is correlated along the main diagonal of a similarity matrix to construct a frameindexed novelty measure. In contrast to many previous approaches, the kernel functions combine all pairwise dissimilarity information in a neighborhood of L frames around the current frame. These secondary features are used as input to an efficient k-Nearest-Neighbor (kNN) classifier. The classifier labels each frame as a shot boundary or non-boundary, and the classifier outputs are minimally processed to determine the final segmentation.