Internet ideo Search and Repurposing Through Face Analysis
With the ever-growing amount ofvideos on the internet,searching for desired videos in an effective and efficient way remains a challenge．In addition，repurposing videos of interest into new attractive photo／video products has been an open issue．In this paper,we propose a framework fbr video retrieval and repurposing by leveraging the face information in videos．Since text query cannot express user’s intentprecisely and it may generate noisy result,an automatic query image generation method is proposed to provide user with visual and intuitive candidate images．Then，based on user-selected query image,videos are re-ranked through content analysis SO that videos with bigher relevance can emerge to the top．Furthermore,relevant segments andframes are obtained and they can be used to compose customized photo/video products,which provides user with a fresh experience as a creator．In this paper,a prototype ofvideo retrieval and repurposing system is implemented for retrieving videos of celebrities and generating customized products．Experiments have been done on 3416 video clips related to about 103 celebrities downloaded from YouTube．The experimental results show the effectiveness of our proposed method．
Video search Video re-ranking Video repurposing Face clustering
Xinyun Sun Xiao Zhang Keyan Liu Tong Zhang ShanWang
Renmin University of China Key Laboratory of DEKE,MOE Nokia-Siemens-Network CTO HP Labs Palo Alto Renmin University oj China Key Laboratory of DEKE,MOE
国内会议
北京
英文
1-8
2011-11-04（万方平台首次上网日期，不代表论文的发表时间）