Name-Face Association in Web Videos: A Large-Scale Dataset,Baselines, and Open Issues

作     者：陈智能 杨宗桦 张炜 曹娟 姜育刚 Zhi-Neng Chen;Chong-Wah Ngo;Member IEEE Wei Zhang;Juan Cao;Yu-Gang Jiang

作者机构：Institute of Automation Chinese Academy of Sciences Department of Computer Science City University of Hong Kong Institute of Computing Technology Chinese Academy of Sciences School of Computer Science Fudan University 

出 版 物：《Journal of Computer Science & Technology》 (计算机科学技术学报（英文版）)

年 卷 期：2014年第29卷第5期

页      面：785-798页

核心收录：

学科分类：0808[工学-电气工程] 081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by a research grant from City University of Hong Kong under Grant No.7008178 the National Natural Science Foundation of China under Grant Nos.61228205,61303175 and 61172153 

主　　题：Web video celebrity name-face association dataset construction community analysis 

摘      要：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 *** describe the details of dataset construction, discuss several interesting findings by analyzing this dataset like celebrity community discovery, and provide experimental results of name-face association using five existing techniques. We also outline important and challenging research problems that could be investigated in the future.