This paper aims to extend our previous researches on clustering web video search results, which reported in [1, 2, 3]. To search videos, users usually use online video search systems such as YouTube, Google Video. However, the returned search results of these systems may include many videos of different categories, and as a result, users find it difficult to locate video clips of interest. Therefore, clustering web video search results is necessary in order to improve the efficiency of searching. The main idea of paper based on analysing and combining the features extracted from video to find the set of appropriate features to improve the quality of video clusters.
An eye-tracking-based approach to facilitate interactive video search
