Abstract We construct a unified interactive video re-targeting system for video summarization, completion and reshuffling. Our system combines the advantages of both video warping and summarizing processing. We first warping the video to present initial editing results, then refine the results

im ssio al w the human face and results in more accurate facial illumination details. In addition, we also propose a new distance-based metric to automatically select the optimal parameters such that the global and local warping effects in the elastic model can be suitably balanced. Experimental