Chen ZN, Ngo C-W, Zhang W et al. Name-Face Association in Web Videos: A Large-Scale Dataset, Baselines, and Open Issues. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY Vol.(No.):1-end Mon. Year Name-Face Association in Web Videos: A Large-Scale Dataset, Baselines, and Open Issues Zhineng Chen1,2 (陈智能), Chong-Wah Ngo2, (杨宗桦), Member, IEEE, Wei Zhang2 (张炜), Juan Cao3 (曹娟), and Yu-Gang Jiang4 (姜育刚) 1Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China 2Department of Computer Science, City University of Hong Kong, Hong Kong, China 3Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China 4School of Computer Science, Fudan University, Shanghai, 200433, China E-mail:
[email protected];
[email protected];
[email protected];
[email protected];
[email protected] Abstract Associating faces appearing in Web videos with names presented in the surrounding context is an important task in many applications. However, the problem is not well investigated particularly under large-scale realistic scenario, mainly due to the scarcity of dataset constructed in such circumstance. In this paper, we introduce a Web video dataset of celebrities, named WebV-Cele, for name-face association. The dataset consists of 75,073 Internet videos of over 4,000 hours, covering 2,427 celebrities and 649,001 faces. This is to our knowledge the most comprehensive dataset for this problem. We describe the details of dataset construction, discuss several interesting findings by analyzing this dataset like celebrity com- munity discovery, and provide experimental results of name-face association using five existing tech- niques.