Graph Partition Model for Robust Temporal Data Segmentation

This paper proposes a novel temporal data segmentation approach based on a graph partition model. To find the optimal segmentation, which maintains maximal connectivity within the same segment while keeping minimum association between different ones, we adopt the min-max cut as an objective function. For temporal data, a linear time algorithm is designed by importing the temporal constraints. With multi-pair comparison strategy, the proposed method is more robust than the existing pair-wise comparison ones. The experiments on TRECVID benchmarking platform demonstrate the effectiveness of our approach.